Pattern Recognition Letters最新文献

Haze blurs image information and reduces the visibility of objects in the image, which seriously affects the performance of computer vision applications in a hazy environment. We propose an improved dehazing model based on multi-label graph cuts. A hazy image is modeled as an undirected graph. The multi-label graph cuts algorithm divides the image into subregions according to the functions of brightness and saturation. A subregion is selected to estimate atmospheric light based on saturation. Under the similarity of transmission in the same subregion, transmission is estimated by the distance between the pixel and atmospheric light in RGB space. Finally, the transmission map is regularized to recover a haze-free image. Experiments in different scenarios demonstrate the effectiveness of the proposed method than the state-of-the-art methods.

Existing 3D instance segmentation methods usually learn the offsets (also known as center-shifted vectors) from points to their instance center for clustering and generating segmentation results. However, due to the instances with different scales, direct regression offsets will make the model pay more attention to the larger instances and ignore the smaller instances. Besides, the clustering also may fail because a single bandwidth for point grouping is insufficient for instances with different scales. To address these two problems, we propose a new framework (DualGroup) for 3D instance segmentation. For the first issue, different from directly learning the offsets, we propose an encoded center-shifted vector learning (ECSVL), which effectively compresses the range of the regression center-shifted vectors for more conducive learning of smaller instances. Second, to handle the instances with different scales in clustering, we propose a dual hierarchical grouping (DHG) to better group all points into different instances. The cooperation of these two components leads to the success of indoor instance segmentation. Moreover, the DualGroup is extended to the 3D panoptic segmentation by fusing the semantic predictions and instance results. Experimental results on the ScanNet v2 and S3DIS datasets demonstrate the effectiveness and superiority of the DualGroup.

Pelvic Organ Prolapse (POP) is a common disease in middle-aged and elderly women. The detection of POP is a challenging task, and using deep learning for detection has its practical significance. However, medical image detection tasks always face many problems, i.e., small sample size, data imbalance, and unobvious pathological characteristics. In this paper, we propose a new training framework, called self-supervised Domain Adaptation with Significance-Oriented Masking (DASOM), to address these problems and improve the performance of POP intelligent detection. DASOM includes a new pre-training process based on the masked image modeling task, and redesigns the masking strategy, bringing the local induction capability required for detection to the model. Meanwhile, we also adopt the data process method fitting the pelvic floor ultrasonic dataset to effectively solve the problem of data shortage and imbalance. Extensive experimental results and analysis confirm that the proposed method significantly improves the performance and reliability of POP detection.

This paper proposes an Intrusion Detection System (IDS) that utilizes Deep Reinforcement Learning (DRL) in a fine-grained manner to enhance the performance of binary and multiclass intrusion classification tasks. The proposed system, named Micro Reinforcement Learning Classifier (MRLC), is evaluated using three standard datasets. MRLC architecture utilizes a fine-grained learning approach to enhance IDS accuracy. Simulation studies demonstrate that MRLC has a high efficiency in discriminating different intrusion classes, outperforming state-of-the-art RL-based methods. The average accuracy of MRLC is 99.56%, 99.99%, 99.01% for NSL-KDD, CIC-IDS2018, and UNSW-NB15 datasets respectively. The implementation codes are available at https://github.com/boshradarabi/MICRO-RL-IDS.

In recent years, many semantic segmentation methods have been proposed to predict label of pixels in the scene. In general, we measure area prediction errors or boundary prediction errors for comparing methods. However, there is no intuitive evaluation metric that evaluates both aspects. In this work, we propose a new evaluation measure called weighted Intersection over Union (wIoU) for semantic segmentation. First, it builds a weight map generated from a boundary distance map, allowing weighted evaluation for each pixel based on a boundary importance factor. The proposed wIoU can evaluate both contour and region by setting a boundary importance factor. We validated the effectiveness of wIoU on a dataset of 33 scenes and demonstrated its flexibility. Using the proposed metric, we expect more flexible and intuitive evaluation in semantic segmentation field are possible.

In practical application scenarios, the occlusion caused by various obstacles greatly undermines the accuracy of person re-identification. Most existing methods for occluded person re-identification focus on inferring visible parts of the body through auxiliary models, resulting in inaccurate feature matching of parts and ignoring the problem of insufficient occluded samples, which seriously affects the accuracy of occluded person re-identification. To address the above issues, we propose a multi-scale occlusion suppression network (MSOSNet) for occluded person re-identification. Specifically, we first propose a dual occlusion augmentation module (DOAM), which combines random occlusion with our proposed novel cross occlusion to generate more diverse occlusion data. Meanwhile, we design a novel occluded-aware spatial attention module (OSAM) to enable the network to focus on non-occluded areas of pedestrian images and effectively extract discriminative features. Ultimately, we propose a part feature matching module (PFMM) that utilizes graph matching algorithms to match non-occluded body parts of pedestrians. Extensive experimental results on both occluded and holistic datasets validate the effectiveness of our method.

Multi-view stereo (MVS) is one of the ways to obtain the 3D structure from 2D images. Deep learning is an effective end-to-end method for MVS. In previous MVS methods based on deep learning, the depth interval is deeply coupled with the feature map resolution, resulting in more accurate depth intervals accompanied by higher computational cost. This paper proposes a new deep neural network HC-MVSNet which utilizes a hybrid cascade structures for depth estimation of MVS. Different from the previous MVS methods, the new coarse-to-fine depth estimation method decouples the two processes of resolution increase and depth interval reduction through a simple operation, achieving higher reconstruction accuracy and completeness for minimal additional computational cost. In addition, an efficient depth sampling strategy based on probability distribution is introduced, which allocates higher hypothesis density for regions with a high probability of ground truth. This novel sampling method makes full use of redundant information that was previously neglected and significantly improves the textural detail of the results. Extensive experiments are conducted on DTU datasets, Tanks and Temples benchmark, and BlendedMVS datasets. The results show that the proposed method exhibits superior performance and better generalization behavior than existing MVS methods.

Snowfall can cause noise to light detection and ranging (LiDAR) data. This is a problem since it is used in many outdoor applications, e.g., autonomous driving. We propose the task of multi-echo denoising, where the goal is to pick the echo that represents the objects of interest and discard other echoes. Thus, the idea is to pick points from alternative echoes unavailable in standard strongest echo point clouds. Intuitively, we are trying to see through the snowfall. We propose a novel self-supervised deep learning method and the characteristics similarity regularization to achieve this goal. The characteristics similarity regularization utilizes noise characteristics to increase performance. The experiments with a real-world multi-echo snowfall dataset prove the efficacy of multi-echo denoising and superior performance to the baseline. Moreover, based on extensive experiments on a semi-synthetic dataset, our method achieves superior performance compared to the state-of-the-art in self-supervised snowfall denoising. Our work enables more reliable point cloud acquisition in snowfall. The code is available at https://github.com/alvariseppanen/SMEDen.

People tend to judge others assessing their personality traits relying on life experience. This fact is especially evident when making an informed hiring decision, which should consider not only skills, but also match a company’s values and culture. Based on this assumption, we use the Siamese Network (SN) for assessing five personality traits by pairwise analyzing and comparing people simultaneously. For this, we propose the OCEAN-AI framework based on Gated Siamese Fusion Network (GSFN), which comprises six modules and enables the fusion of hand-crafted and deep features across three modalities (video, audio, and text). We use the ChaLearn First Impressions v2 (FIv2) and Multimodal Personality Traits Assessment (MuPTA) corpora and identify that all six feature sets and their combinations due to different information content allow the framework to adjust to heterogeneous input data flexibly. The experimental results show that the pairwise comparison of people with the same or different Personality Traits (PT) during the training enhances the proposed framework performance. The framework outperforms the State-of-the-Art (SOTA) systems based on three modalities (video-face, audio and text) by the relative value of 1.3% (0.928 vs. 0.916) in terms of the mean accuracy (mACC) on the FIv2 corpus. We also outperform the SOTA system in terms of the Concordance Correlation Coefficient (CCC) by the relative value of 8.6% (0.667 vs. 0.614) using two modalities (video and audio) on the MuPTA corpus. We make our framework publicly available to integrate it into various applications such as recruitment, education, and healthcare.

Falls have become one of the main causes of injury and death among the elderly. A high-accuracy fall detection method can effectively detect falls in the elderly, thereby reducing the probability of injury and mortality. This paper proposes a fall detection algorithm based on global and local feature extraction. Specifically, we design a dual-stream network, with one branch composed of a convolutional neural network and a regional attention module for extracting local features from images. The other branch consists of an improved Transformer for extracting global features from images. The local and global features are then fused using a feature fusion module for classification, enabling fall detection. Experimental results show that the proposed approach achieves accuracies of 99.55% and 99.75% when tested with UP-Fall Detection Dataset and Le2i Fall Detection Dataset.