Pub Date : 2011-01-05DOI: 10.1109/WACV.2011.5711485
M. Bergh, L. Gool
Time-of-Flight (ToF) and other IR-based cameras that register depth are becoming more and more affordable in consumer electronics. This paper aims to improve a realtime hand gesture interaction system by augmenting it with a ToF camera. First, the ToF camera and the RGB camera are calibrated, and a mapping is made from the depth data to the RGB image. Then, a novel hand detection algorithm is introduced based on depth and color. This not only improves detection rates, but also allows for the hand to overlap with the face, or with hands from other persons in the background. The hand detection algorithm is evaluated in these settings, and compared to previous algorithms. Furthermore, the depth information allows us to track the position of the hand in 3D, allowing for more interesting modes of interaction. Finally, the hand gesture recognition algorithm is applied to the depth data as well, and compared to the recognition based on the RGB images. The result is a real-time hand gesture interaction system that allows for complex 3D gestures and is not disturbed by objects or persons in the background.
{"title":"Combining RGB and ToF cameras for real-time 3D hand gesture interaction","authors":"M. Bergh, L. Gool","doi":"10.1109/WACV.2011.5711485","DOIUrl":"https://doi.org/10.1109/WACV.2011.5711485","url":null,"abstract":"Time-of-Flight (ToF) and other IR-based cameras that register depth are becoming more and more affordable in consumer electronics. This paper aims to improve a realtime hand gesture interaction system by augmenting it with a ToF camera. First, the ToF camera and the RGB camera are calibrated, and a mapping is made from the depth data to the RGB image. Then, a novel hand detection algorithm is introduced based on depth and color. This not only improves detection rates, but also allows for the hand to overlap with the face, or with hands from other persons in the background. The hand detection algorithm is evaluated in these settings, and compared to previous algorithms. Furthermore, the depth information allows us to track the position of the hand in 3D, allowing for more interesting modes of interaction. Finally, the hand gesture recognition algorithm is applied to the depth data as well, and compared to the recognition based on the RGB images. The result is a real-time hand gesture interaction system that allows for complex 3D gestures and is not disturbed by objects or persons in the background.","PeriodicalId":236308,"journal":{"name":"IEEE Workshop/Winter Conference on Applications of Computer Vision","volume":"127 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113970042","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}
Pub Date : 2009-12-01DOI: 10.1109/WACV.2009.5403132
B. Morse
Welcome to the proceedings of the Ninth IEEE Computer Society Workshop on Application of Computer Vision (WACV 2009), held at Snowbird, Utah from December 7–8, 2009. We are delighted to be part of this year's IEEE Winter Vision Meetings, which also included WMVC and Winter-PETS.
{"title":"Introductory message from WACV 2009 general chair","authors":"B. Morse","doi":"10.1109/WACV.2009.5403132","DOIUrl":"https://doi.org/10.1109/WACV.2009.5403132","url":null,"abstract":"Welcome to the proceedings of the Ninth IEEE Computer Society Workshop on Application of Computer Vision (WACV 2009), held at Snowbird, Utah from December 7–8, 2009. We are delighted to be part of this year's IEEE Winter Vision Meetings, which also included WMVC and Winter-PETS.","PeriodicalId":236308,"journal":{"name":"IEEE Workshop/Winter Conference on Applications of Computer Vision","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123546891","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}
Pub Date : 2000-12-04DOI: 10.1109/WACV.2000.895418
Jaesik Min, M. Powell, K. Bowyer
We have developed an automated framework for objectively evaluating the performance of region segmentation algorithms. This framework is demonstrated with range image data sets, but is applicable to any type of imagery. Parameters of the segmentation algorithm are tuned using training images. Images and source code for the training process care publicly available. The trained parameters are then used to evaluate the algorithm on a (sequestered) test set. The primary performance metric is the average number of correctly segmented regions. Statistical tests are used to determine the significance of performance improvement over a baseline algorithm.
{"title":"Automated performance evaluation of range image segmentation","authors":"Jaesik Min, M. Powell, K. Bowyer","doi":"10.1109/WACV.2000.895418","DOIUrl":"https://doi.org/10.1109/WACV.2000.895418","url":null,"abstract":"We have developed an automated framework for objectively evaluating the performance of region segmentation algorithms. This framework is demonstrated with range image data sets, but is applicable to any type of imagery. Parameters of the segmentation algorithm are tuned using training images. Images and source code for the training process care publicly available. The trained parameters are then used to evaluate the algorithm on a (sequestered) test set. The primary performance metric is the average number of correctly segmented regions. Statistical tests are used to determine the significance of performance improvement over a baseline algorithm.","PeriodicalId":236308,"journal":{"name":"IEEE Workshop/Winter Conference on Applications of Computer Vision","volume":"309 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121264796","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}
A. Hoover, G. Jean-Baptiste, Dmitry Goldgof, K. Bowyer
This paper describes a definition of the range image segmentation (of polyhedral scenes) problem, a data set to use in evaluation, a method for specifying ground truth, and a set of metrics to classify segmentation results against ground truths. >
{"title":"A methodology for evaluating range image segmentation techniques","authors":"A. Hoover, G. Jean-Baptiste, Dmitry Goldgof, K. Bowyer","doi":"10.1109/ACV.1994.341320","DOIUrl":"https://doi.org/10.1109/ACV.1994.341320","url":null,"abstract":"This paper describes a definition of the range image segmentation (of polyhedral scenes) problem, a data set to use in evaluation, a method for specifying ground truth, and a set of metrics to classify segmentation results against ground truths. >","PeriodicalId":236308,"journal":{"name":"IEEE Workshop/Winter Conference on Applications of Computer Vision","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122923811","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}
Pub Date : 1900-01-01DOI: 10.1109/WACV56688.2023.00081
Min Woo Kim, N. Cho
Even a rough sketch can effectively convey the descriptions of objects, as humans can imagine the original shape from the sketch. The sketch-to-photo translation is a computer vision task that enables a machine to do this imagination, taking a binary sketch image and generating plausible RGB images corresponding to the sketch. Hence, deep neural networks for this task should learn to generate a wide range of frequencies because most parts of the input (binary sketch image) are composed of DC signals. In this paper, we propose a new loss function named Wavelet-domain High-Frequency Loss (WHFL) to overcome the limitations of previous methods that tend to have a bias toward low frequencies. The proposed method emphasizes the loss on the high frequencies by designing a new weight matrix imposing larger weights on the high bands. Unlike existing handcraft methods that control frequency weights using binary masks, we use the matrix with finely controlled elements according to frequency scales. The WHFL is designed in a multi-scale form, which lets the loss function focus more on the high frequency according to decomposition levels. We use the WHFL as a complementary loss in addition to conventional ones defined in the spatial domain. Experiments show we can improve the qualitative and quantitative results in both spatial and frequency domains. Additionally, we attempt to verify the WHFL’s high-frequency generation capability by defining a new evaluation metric named Unsigned Euclidean Distance Field Error (UEDFE).
{"title":"WHFL: Wavelet-Domain High Frequency Loss for Sketch-to-Image Translation","authors":"Min Woo Kim, N. Cho","doi":"10.1109/WACV56688.2023.00081","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00081","url":null,"abstract":"Even a rough sketch can effectively convey the descriptions of objects, as humans can imagine the original shape from the sketch. The sketch-to-photo translation is a computer vision task that enables a machine to do this imagination, taking a binary sketch image and generating plausible RGB images corresponding to the sketch. Hence, deep neural networks for this task should learn to generate a wide range of frequencies because most parts of the input (binary sketch image) are composed of DC signals. In this paper, we propose a new loss function named Wavelet-domain High-Frequency Loss (WHFL) to overcome the limitations of previous methods that tend to have a bias toward low frequencies. The proposed method emphasizes the loss on the high frequencies by designing a new weight matrix imposing larger weights on the high bands. Unlike existing handcraft methods that control frequency weights using binary masks, we use the matrix with finely controlled elements according to frequency scales. The WHFL is designed in a multi-scale form, which lets the loss function focus more on the high frequency according to decomposition levels. We use the WHFL as a complementary loss in addition to conventional ones defined in the spatial domain. Experiments show we can improve the qualitative and quantitative results in both spatial and frequency domains. Additionally, we attempt to verify the WHFL’s high-frequency generation capability by defining a new evaluation metric named Unsigned Euclidean Distance Field Error (UEDFE).","PeriodicalId":236308,"journal":{"name":"IEEE Workshop/Winter Conference on Applications of Computer Vision","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129729680","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：