In medical imaging, the automatic diagnosis of kidney carcinoma has become more diffi-cult because it is not easy to detect by physicians. Pre-processing is the first identification method to enhance image quality, remove noise and unwanted components from the back-drop of the kidneys image. The pre-processing method is essential and significant for the proposed algorithm. The objective of this analysis is to recognize and classify kidney dis-turbances with an ultrasound scan by providing a number of substantial content description parameters. The ultrasound pictures are prepared to protect the interest pixels before extracting the feature. A series of quantitative features were synthesized of each images, the principal component analysis was conducted for minimizing the number of features to produce set of wavelet-based multi-scale features. Dragonfly algorithm (DFA) was exe-cuted in this method. In the proposed work, the design and training of a random decision forest classifier and selected features are implemented. The classification of e-health information using ideal characteristics is used by the RF classifier. The proposed technique is activated in MATLAB/simulink work site and the experimental results show that the peak accuracy of the proposed technique is 95.6% using GWO-FFBN techniques compared to other existing techniques.
{"title":"An automatic feature selection and classification framework for analyzing ultrasound kidney images using dragonfly algorithm and random forest classifier","authors":"C. Venkata Narasimhulu","doi":"10.1049/IPR2.12179","DOIUrl":"https://doi.org/10.1049/IPR2.12179","url":null,"abstract":"In medical imaging, the automatic diagnosis of kidney carcinoma has become more diffi-cult because it is not easy to detect by physicians. Pre-processing is the first identification method to enhance image quality, remove noise and unwanted components from the back-drop of the kidneys image. The pre-processing method is essential and significant for the proposed algorithm. The objective of this analysis is to recognize and classify kidney dis-turbances with an ultrasound scan by providing a number of substantial content description parameters. The ultrasound pictures are prepared to protect the interest pixels before extracting the feature. A series of quantitative features were synthesized of each images, the principal component analysis was conducted for minimizing the number of features to produce set of wavelet-based multi-scale features. Dragonfly algorithm (DFA) was exe-cuted in this method. In the proposed work, the design and training of a random decision forest classifier and selected features are implemented. The classification of e-health information using ideal characteristics is used by the RF classifier. The proposed technique is activated in MATLAB/simulink work site and the experimental results show that the peak accuracy of the proposed technique is 95.6% using GWO-FFBN techniques compared to other existing techniques.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79317372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An accurate and robust sperm cells tracking algorithm that is able to detect and track sperm cells in videos with high accuracy and efficiency is presented. It is fast enough to process approximately 30 frames per second. It can find the correct path and measure motility parameters for each sperm. It can also adapt with different types of images coming from different cameras and bad recording conditions. Specifically, a new way is offered to optimize uneven lighting images to improve sperm cells detection which gives us the ability to get more accurate tracking results. The shape of each detected object is used to specify collided sperms and utilized dynamic gates which become bigger and smaller according to the sperm cell’s speed. For assigning tracks to the detected sperm cells positions an improved version of branch and bound algorithm which is faster than the normal one is offered. This sperm cells tracking algorithm outperforms many of the previous algorithms as it has lower error rate in both sperm detection and tracking. It is compared with six other algorithms, and it gives lower tracking error rates. This method will allow doctors and researchers to obtain sperm motility data instantly and accurately.
{"title":"A robust sperm cell tracking algorithm using uneven lighting image fixing and improved branch and bound algorithm","authors":"Ahmad Alhaj Alabdulla, A. Hasiloglu, E. Aksu","doi":"10.1049/IPR2.12178","DOIUrl":"https://doi.org/10.1049/IPR2.12178","url":null,"abstract":"An accurate and robust sperm cells tracking algorithm that is able to detect and track sperm cells in videos with high accuracy and efficiency is presented. It is fast enough to process approximately 30 frames per second. It can find the correct path and measure motility parameters for each sperm. It can also adapt with different types of images coming from different cameras and bad recording conditions. Specifically, a new way is offered to optimize uneven lighting images to improve sperm cells detection which gives us the ability to get more accurate tracking results. The shape of each detected object is used to specify collided sperms and utilized dynamic gates which become bigger and smaller according to the sperm cell’s speed. For assigning tracks to the detected sperm cells positions an improved version of branch and bound algorithm which is faster than the normal one is offered. This sperm cells tracking algorithm outperforms many of the previous algorithms as it has lower error rate in both sperm detection and tracking. It is compared with six other algorithms, and it gives lower tracking error rates. This method will allow doctors and researchers to obtain sperm motility data instantly and accurately.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86183121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. H. Junos, A. S. M. Khairuddin, Subbiah Thannirmalai, M. Dahari
Funding information RU Grant-Faculty Programme by Faculty of Engineering, University of Malaya, Grant/Award Number: GPF042A-2019; Industry-Driven Innovation, Grant/Award Number: (IDIG)-PPSI-2020CLUSTER-SD01 Abstract The adoption of automated crop harvesting system based on machine vision may improve productivity and optimize the operational cost. The scope of this study is to obtain visual information at the plantation which is crucial in developing an intelligent automated crop harvesting system. This paper aims to develop an automatic detection system with high accuracy performance, low computational cost and lightweight model. Considering the advantages of YOLOv3 tiny, an optimized YOLOv3 tiny network namely YOLO-P is proposed to detect and localize three objects at palm oil plantation which include fresh fruit bunch, grabber and palm tree under various environment conditions. The proposed YOLO-P model incorporated lightweight backbone based on densely connected neural network, multi-scale detection architecture and optimized anchor box size. The experimental results demonstrated that the proposed YOLO-P model achieved good mean average precision and F1 score of 98.68% and 0.97 respectively. Besides, the proposed model performed faster training process and generated lightweight model of 76 MB. The proposed model was also tested to identify fresh fruit bunch of various maturities with accuracy of 98.91%. The comprehensive experimental results show that the proposed YOLO-P model can effectively perform robust and accurate detection at the palm oil plantation.
{"title":"An optimized YOLO-based object detection model for crop harvesting system","authors":"M. H. Junos, A. S. M. Khairuddin, Subbiah Thannirmalai, M. Dahari","doi":"10.1049/IPR2.12181","DOIUrl":"https://doi.org/10.1049/IPR2.12181","url":null,"abstract":"Funding information RU Grant-Faculty Programme by Faculty of Engineering, University of Malaya, Grant/Award Number: GPF042A-2019; Industry-Driven Innovation, Grant/Award Number: (IDIG)-PPSI-2020CLUSTER-SD01 Abstract The adoption of automated crop harvesting system based on machine vision may improve productivity and optimize the operational cost. The scope of this study is to obtain visual information at the plantation which is crucial in developing an intelligent automated crop harvesting system. This paper aims to develop an automatic detection system with high accuracy performance, low computational cost and lightweight model. Considering the advantages of YOLOv3 tiny, an optimized YOLOv3 tiny network namely YOLO-P is proposed to detect and localize three objects at palm oil plantation which include fresh fruit bunch, grabber and palm tree under various environment conditions. The proposed YOLO-P model incorporated lightweight backbone based on densely connected neural network, multi-scale detection architecture and optimized anchor box size. The experimental results demonstrated that the proposed YOLO-P model achieved good mean average precision and F1 score of 98.68% and 0.97 respectively. Besides, the proposed model performed faster training process and generated lightweight model of 76 MB. The proposed model was also tested to identify fresh fruit bunch of various maturities with accuracy of 98.91%. The comprehensive experimental results show that the proposed YOLO-P model can effectively perform robust and accurate detection at the palm oil plantation.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80785606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper describes an image encryption algorithm that utilises a plaintext-related quantisation scheme. Various plaintext-related approaches from other algorithms are presented and their properties are briefly discussed. Main advantage of the proposed solution is the achievement of a similar behaviour like that of more complex approaches with a plaintext-related technique used in a rather simple step such as quantisation. This design should result in a favourable computational complexity of the whole algorithm. The properties of the proposal are evaluated by a number of commonly used numerical parameters. Also, the statistical properties of a pseudo-random sequence that is quantised according to the plain image pixel intensities are investigated by tests from NIST 800-22 suite. Obtained results are compared to values reported in related works and they imply that the proposed solution produces encrypted images with comparable statistical properties but authors’ design is faster and more efficient.
{"title":"An image encryption algorithm with a plaintext-related quantisation scheme","authors":"Jakub Oravec, Ľ. Ovseník, J. Papaj","doi":"10.1049/IPR2.12174","DOIUrl":"https://doi.org/10.1049/IPR2.12174","url":null,"abstract":"This paper describes an image encryption algorithm that utilises a plaintext-related quantisation scheme. Various plaintext-related approaches from other algorithms are presented and their properties are briefly discussed. Main advantage of the proposed solution is the achievement of a similar behaviour like that of more complex approaches with a plaintext-related technique used in a rather simple step such as quantisation. This design should result in a favourable computational complexity of the whole algorithm. The properties of the proposal are evaluated by a number of commonly used numerical parameters. Also, the statistical properties of a pseudo-random sequence that is quantised according to the plain image pixel intensities are investigated by tests from NIST 800-22 suite. Obtained results are compared to values reported in related works and they imply that the proposed solution produces encrypted images with comparable statistical properties but authors’ design is faster and more efficient.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73384948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An extension of Radon transform by using a measure function capturing the user need is proposed. The new transform, called scale space Radon transform, is devoted to the case where the embedded shape in the image is not filiform. A case study is brought on a straight line and an ellipse where the SSRT behaviour in the scale space and in the presence of noise is deeply analyzed. In order to show the effectiveness of the proposed transform, the experiments have been carried out, first, on linear and elliptical structures generated synthetically subjected to strong altering conditions such blur and noise and then on structures images issued from real-world applications such as road traffic, satellite imagery and weld X-ray imaging. Comparisons in terms of detection accuracy and computational time with well-known transforms and recent work dedicated to this purpose are conducted, where the proposed transform shows an outstanding performance in detecting the above-mentioned structures and targeting accurately their spatial locations even in low-quality images.
{"title":"Scale space Radon transform","authors":"D. Ziou, Nafaa Nacereddine, A. Goumeidane","doi":"10.1049/IPR2.12180","DOIUrl":"https://doi.org/10.1049/IPR2.12180","url":null,"abstract":"An extension of Radon transform by using a measure function capturing the user need is proposed. The new transform, called scale space Radon transform, is devoted to the case where the embedded shape in the image is not filiform. A case study is brought on a straight line and an ellipse where the SSRT behaviour in the scale space and in the presence of noise is deeply analyzed. In order to show the effectiveness of the proposed transform, the experiments have been carried out, first, on linear and elliptical structures generated synthetically subjected to strong altering conditions such blur and noise and then on structures images issued from real-world applications such as road traffic, satellite imagery and weld X-ray imaging. Comparisons in terms of detection accuracy and computational time with well-known transforms and recent work dedicated to this purpose are conducted, where the proposed transform shows an outstanding performance in detecting the above-mentioned structures and targeting accurately their spatial locations even in low-quality images.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73904437","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fukun Bi, Jiayi Sun, Jianhong Han, Yanping Wang, M. Bian
Funding information National Natural Science Foundation of China, Grant/Award Number: 61971006; Natural Science Foundation of Beijing Municipal, Grant/Award Number: 4192021 Abstract Remote sensing target tracking in satellite videos plays a key role in various fields. However, due to the complex backgrounds of satellite video sequences and many rotation changes of highly dynamic targets, typical target tracking methods for natural scenes cannot be used directly for such tasks, and their robustness and accuracy are difficult to guarantee. To address these problems, an algorithm is proposed for remote sensing target tracking in satellite videos based on a variable-angle-adaptive Siamese network (VAASN). Specifically, the method is based on the fully convolutional Siamese network (Siamese-FC). First, for the feature extraction stage, to reduce the impact of complex backgrounds, we present a new multifrequency feature representation method and introduce the octave convolution (OctConv) into the AlexNet architecture to adapt to the new feature representation. Then, for the tracking stage, to adapt to changes in target rotation, a variable-angle-adaptive module that uses a fast text detector with a single deep neural network (TextBoxes++) is introduced to extract angle information from the template frame and detection frames and performs angle consistency update operations on the detection frames. Finally, qualitative and quantitative experiments using satellite datasets show that the proposed method can improve tracking accuracy while achieving high efficiency.
{"title":"Remote sensing target tracking in satellite videos based on a variable-angle-adaptive Siamese network","authors":"Fukun Bi, Jiayi Sun, Jianhong Han, Yanping Wang, M. Bian","doi":"10.1049/IPR2.12170","DOIUrl":"https://doi.org/10.1049/IPR2.12170","url":null,"abstract":"Funding information National Natural Science Foundation of China, Grant/Award Number: 61971006; Natural Science Foundation of Beijing Municipal, Grant/Award Number: 4192021 Abstract Remote sensing target tracking in satellite videos plays a key role in various fields. However, due to the complex backgrounds of satellite video sequences and many rotation changes of highly dynamic targets, typical target tracking methods for natural scenes cannot be used directly for such tasks, and their robustness and accuracy are difficult to guarantee. To address these problems, an algorithm is proposed for remote sensing target tracking in satellite videos based on a variable-angle-adaptive Siamese network (VAASN). Specifically, the method is based on the fully convolutional Siamese network (Siamese-FC). First, for the feature extraction stage, to reduce the impact of complex backgrounds, we present a new multifrequency feature representation method and introduce the octave convolution (OctConv) into the AlexNet architecture to adapt to the new feature representation. Then, for the tracking stage, to adapt to changes in target rotation, a variable-angle-adaptive module that uses a fast text detector with a single deep neural network (TextBoxes++) is introduced to extract angle information from the template frame and detection frames and performs angle consistency update operations on the detection frames. Finally, qualitative and quantitative experiments using satellite datasets show that the proposed method can improve tracking accuracy while achieving high efficiency.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86497990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Underwater image enhancement is an important low-level vision task with much attention of community. Clear underwater images are helpful for underwater operations. However, raw underwater images often suffer from different types of distortions caused by the underwater environment. To solve these problems, this paper proposes an end-to-end dual generative adversarial network (DuGAN) for underwater image enhancement. The images processed by existing methods are taken as training samples for reference, and they are segmented into clear parts and unclear parts. Two discriminators are used to complete adversarial training toward different areas of images with different training strategies, respectively. The proposed method is able to output more pleasing images than reference images benefit by this framework. Meanwhile, to ensure the authenticity of the enhanced images, content loss, adversarial loss, and style loss are combined as loss function of our framework. This framework is easy to use, and the subjective and objective experiments show that excellent results are achieved compared to those methods mentioned in the literature.
{"title":"DuGAN: An effective framework for underwater image enhancement","authors":"Huiqing Zhang, Luyu Sun, Lifang Wu, Ke Gu","doi":"10.1049/IPR2.12172","DOIUrl":"https://doi.org/10.1049/IPR2.12172","url":null,"abstract":"Underwater image enhancement is an important low-level vision task with much attention of community. Clear underwater images are helpful for underwater operations. However, raw underwater images often suffer from different types of distortions caused by the underwater environment. To solve these problems, this paper proposes an end-to-end dual generative adversarial network (DuGAN) for underwater image enhancement. The images processed by existing methods are taken as training samples for reference, and they are segmented into clear parts and unclear parts. Two discriminators are used to complete adversarial training toward different areas of images with different training strategies, respectively. The proposed method is able to output more pleasing images than reference images benefit by this framework. Meanwhile, to ensure the authenticity of the enhanced images, content loss, adversarial loss, and style loss are combined as loss function of our framework. This framework is easy to use, and the subjective and objective experiments show that excellent results are achieved compared to those methods mentioned in the literature.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80293871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Correspondence Anjali Gautam, Department of Information Technology, Indian Institute of Information Technology, Allahabad, Prayagraj, Uttar Pradesh, India. Email: anjaligautam@iiita.ac.in Abstract Skin cancer is the most well-known disease found in the individuals who are exposed to the Sun’s ultra-violet (UV) radiations. It is identified when skin tissues on the epidermis grow in an uncontrolled manner and appears to be of different colour than the normal skin tissues. This paper focuses on predicting the class of dermascopic images as benign and malignant. A new feature extraction method has been proposed to carry out this work which can extract relevant features from image texture. Local and gradient information from x and y directions of images has been utilized for feature extraction. After that images are classified using machine learning algorithms by using those extracted features. The efficacy of the proposed feature extraction method has been proved by conducting several experiments on the publicly available image dataset 2016 International Skin Imaging Collaboration (ISIC 2016). The classification results obtained by the method are also compared with state-of-the-art feature extraction methods which show that it performs better than others. The evaluation criteria used to obtain the results are accuracy, true positive rate (TPR) and false positive rate (FPR) where TPR and FPR are used for generating receiver operating characteristic curves.
{"title":"Towards accurate classification of skin cancer from dermatology images","authors":"Anjali Gautam, B. Raman","doi":"10.1049/IPR2.12166","DOIUrl":"https://doi.org/10.1049/IPR2.12166","url":null,"abstract":"Correspondence Anjali Gautam, Department of Information Technology, Indian Institute of Information Technology, Allahabad, Prayagraj, Uttar Pradesh, India. Email: anjaligautam@iiita.ac.in Abstract Skin cancer is the most well-known disease found in the individuals who are exposed to the Sun’s ultra-violet (UV) radiations. It is identified when skin tissues on the epidermis grow in an uncontrolled manner and appears to be of different colour than the normal skin tissues. This paper focuses on predicting the class of dermascopic images as benign and malignant. A new feature extraction method has been proposed to carry out this work which can extract relevant features from image texture. Local and gradient information from x and y directions of images has been utilized for feature extraction. After that images are classified using machine learning algorithms by using those extracted features. The efficacy of the proposed feature extraction method has been proved by conducting several experiments on the publicly available image dataset 2016 International Skin Imaging Collaboration (ISIC 2016). The classification results obtained by the method are also compared with state-of-the-art feature extraction methods which show that it performs better than others. The evaluation criteria used to obtain the results are accuracy, true positive rate (TPR) and false positive rate (FPR) where TPR and FPR are used for generating receiver operating characteristic curves.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77876219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Efficient Intelligent detection is a key technology in automatic harvesting robots. How-ever, citrus detection is still a challenging task because of varying illumination, random occlusion and colour similarity between fruits and leaves in natural conditions. In this paper, a detection method called Lemon-YOLO (L-YOLO) is proposed to improve the accuracy and real-time performance of lemon detection in the natural environment. The SE_ResGNet34 network is designed to replace DarkNet53 network in YOLOv3 algorithm as a new backbone of feature extraction. It can enhance the propagation of features, and needs less parameter, which helps to achieve higher accuracy and speed. Moreover, the SE_ResNet module is added to the detection block, to improve the quality of representa-tions produced from the network by strengthening the convolutional features of channels. The experimental results show that the proposed L-YOLO has an average accuracy(AP) of 96.28% and a detection speed of 106 frames per second (FPS) on the lemon test set, which is 5.68% and 28 FPS higher than the YOLOv3, respectively. The results indicate that the L-YOLO method has superior detection performance. It can recognize and locate lemons in the natural environment more efficiently, providing technical support for the machine’s picking lemon and other fruits.
{"title":"Lemon-YOLO: An efficient object detection method for lemons in the natural environment","authors":"Guojin Li, Xiaojie Huang, Jiaoyan Ai, Zeren Yi, Wei Xie","doi":"10.1049/IPR2.12171","DOIUrl":"https://doi.org/10.1049/IPR2.12171","url":null,"abstract":"Efficient Intelligent detection is a key technology in automatic harvesting robots. How-ever, citrus detection is still a challenging task because of varying illumination, random occlusion and colour similarity between fruits and leaves in natural conditions. In this paper, a detection method called Lemon-YOLO (L-YOLO) is proposed to improve the accuracy and real-time performance of lemon detection in the natural environment. The SE_ResGNet34 network is designed to replace DarkNet53 network in YOLOv3 algorithm as a new backbone of feature extraction. It can enhance the propagation of features, and needs less parameter, which helps to achieve higher accuracy and speed. Moreover, the SE_ResNet module is added to the detection block, to improve the quality of representa-tions produced from the network by strengthening the convolutional features of channels. The experimental results show that the proposed L-YOLO has an average accuracy(AP) of 96.28% and a detection speed of 106 frames per second (FPS) on the lemon test set, which is 5.68% and 28 FPS higher than the YOLOv3, respectively. The results indicate that the L-YOLO method has superior detection performance. It can recognize and locate lemons in the natural environment more efficiently, providing technical support for the machine’s picking lemon and other fruits.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86854008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhiheng Zhou, Yongfan Guo, Ming Dai, Junchu Huang, Xiangwei Li
Funding information National Natural Science Foundation of China, Grant/Award Number: 61871188; National Key R&D Program of China, Grant/Award Number: 2018YFC0309400; Guangzhou city science and technology research projects, Grant/Award Number: 201902020008 Abstract The weakly supervised methods for salient object detection are attractive, since they greatly release the burden of annotating time-consuming pixel-wise masks. However, the imagelevel annotations utilized by current weakly supervised salient object detection models are too weak to provide sufficient supervision for this dense prediction task. To this end, a weakly supervised salient object detection method is proposed via double object proposals guidance, which is generated under the supervision of double bounding boxes annotations. With the double object proposals, the authors’ method is capable of capturing both accurate but incomplete salient foreground and background information, which contributes to generating saliency maps with uniformly highlighted saliency regions and effectively suppressed background. In addition, an unsupervised salient object segmentation method is proposed, taking advantage of the non-parametric statistical active contour model (NSACM), for segmenting salient objects with complete and compact boundaries. Experiments on five benchmark datasets show that the authors’ weakly supervised salient object detection approach consistently outperforms other weakly supervised and unsupervised methods by a considerable margin, and even has comparable performance to the fully supervised ones.
{"title":"Weakly supervised salient object detection via double object proposals guidance","authors":"Zhiheng Zhou, Yongfan Guo, Ming Dai, Junchu Huang, Xiangwei Li","doi":"10.1049/IPR2.12164","DOIUrl":"https://doi.org/10.1049/IPR2.12164","url":null,"abstract":"Funding information National Natural Science Foundation of China, Grant/Award Number: 61871188; National Key R&D Program of China, Grant/Award Number: 2018YFC0309400; Guangzhou city science and technology research projects, Grant/Award Number: 201902020008 Abstract The weakly supervised methods for salient object detection are attractive, since they greatly release the burden of annotating time-consuming pixel-wise masks. However, the imagelevel annotations utilized by current weakly supervised salient object detection models are too weak to provide sufficient supervision for this dense prediction task. To this end, a weakly supervised salient object detection method is proposed via double object proposals guidance, which is generated under the supervision of double bounding boxes annotations. With the double object proposals, the authors’ method is capable of capturing both accurate but incomplete salient foreground and background information, which contributes to generating saliency maps with uniformly highlighted saliency regions and effectively suppressed background. In addition, an unsupervised salient object segmentation method is proposed, taking advantage of the non-parametric statistical active contour model (NSACM), for segmenting salient objects with complete and compact boundaries. Experiments on five benchmark datasets show that the authors’ weakly supervised salient object detection approach consistently outperforms other weakly supervised and unsupervised methods by a considerable margin, and even has comparable performance to the fully supervised ones.","PeriodicalId":13486,"journal":{"name":"IET Image Process.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90891966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：