Search

Video-based person re-identification plays a critical role in intelligent video surveillance by learning temporal correlations from consecutive video frames. Most existing methods aim to solve the challenging variations of pose, occlusion, backgrounds and so on by using attention mechanism. They almost all draw attention to the occlusion and learn occlusion-invariant video representations by abandoning the occluded area or frames, while the other areas in these frames contain sufficient spatial information and temporal cues. To overcome these drawbacks, this paper proposes a comprehensive attention mechanism covering what, where, and when to pay attention in the discriminative spatial-temporal feature learning, namely What-Where-When Attention Network (W3AN). Concretely, W3AN designs a spatial attention module to focus on pedestrian identity and obvious attributes by the importance estimating layer (What and Where), and a temporal attention module to calculate the frame-level importance (when), which is embedded into a graph attention network to exploit temporal attention features rather than computing weighted average feature for video frames like existing methods. Moreover, the experiments on three widely-recognized datasets demonstrate the effectiveness of our proposed W3AN model and the discussion of major modules elaborates the contributions of this paper.

Pavement crack assessment is an important indicator for evaluating road health. However, due to the dark color of the asphalt pavement and the texture characteristics of the pavement, current asphalt pavement crack detection technology cannot meet the requirements of accuracy and efficiency. In this paper, we propose an end-to-end multi-scale full convolutional neural network to achieve the semantic segmentation of cracks in road images by learning the crack characteristics in the complex fine grain background of asphalt pavement. The method uses DenseNet and deconvolution network framework to achieve pixel-level detection and fuses features learned from different scales of convolutional kernels through a full convolutional network to obtain richer information on multi-scale features, allowing more detailed representation of crack features in high-resolution images. And the back end joins the SVM classifier to achieve crack classification after crack segmentation. Then we create a road test standard data set containing 12 cracks and evaluate it on the data. The experimental results show that the method achieves good segmentation effect for 12 types of cracks, and the crack segmentation for asphalt pavement is better than the most advanced methods.

Convolutional neural networks have achieved remarkable results in the detection of X-ray luggage contraband. However, with an increase in contraband classes and substantial artificial transformation, the offline network training method has been unable to accurately detect the rapidly growing new classes of contraband. The current model cannot incrementally learn the newly appearing classes in real time without retraining the model. When the quantity of different types of contraband is not evenly distributed in the real-time detection process, the convolution neural network that is optimized by the gradient descent method will produce catastrophic forgetting, which means learning new knowledge and forgetting old knowledge, and the detection effect on the old classes will suddenly decline. To overcome this problem, this paper proposes an incremental learning method for online continuous learning of models and incrementally learns and detects new classes in the absence of old classes in the new classes. First, we perform parameter compression on the original network by distillation to ensure stable identification of the old classes. Second, the area proposal subnetwork and object detection subnetwork are incrementally learned to obtain the recognition ability of the new classes. In addition, this paper designs a new loss function, which causes the network to avoid catastrophic forgetting and stably detect the object of the new contraband classes. To reliably verify the model, this paper produces a multi-angle dataset for security perspective images. A total of 10 classes of contraband are tested, and the interference between two object detections is analyzed by model parameters. The experimental results show that the model can stably perform new contraband object learning even when there is an uneven distribution of data types.

As supervised person re-identification (Re-Id) requires massive labeled pedestrian data and it is very difficult to collect sufficient labeled data in reality, unsupervised Re-Id approaches attract much more attention than the former. Existing unsupervised person Re-Id models learn global features of pedestrian from whole images or several constant patches. These models ignore the difference of each region in the whole pedestrian images for feature representation, such as occluded and pose invariant regions, and thus reduce the robustness of models for cross-view feature learning. To solve these issues, we propose an Unsupervised Region Attention Network (URAN) that can learn the cross-view region attention features from the cropped pedestrian images, fixed by region importance weights on images. The proposed URAN designs a Pedestrian Region Biased Enhance (PRBE) loss to produce high attention weights for most important regions in pedestrian images. Furthermore, the URAN employs a first neighbor relation grouping algorithm and a First Neighbor Relation Constraint (FNRC) loss to provide the training direction of the unsupervised region attention network, such that the region attention features are discriminant enough for unsupervised person Re-Id task. In experiments, we consider two popular datasets, Market1501 and DukeMTMC-reID, as evaluation of PRBE and FNRC loss, and their balance parameter to demonstrate the effectiveness and efficiency of the proposed URAN, and the experimental results show that the URAN provides better performance than the-state-of-the-arts (higher than existing methods at least 1.1%).