This paper presents a multi-information flow convolutional neural network (MiF-CNN) model for person reidentification (re-id). It contains several specific multilayer convolutional structures, where the input and output of a convolutional layer are concatenated together on channel dimension. With this idea, layers of model can go deeper and feature maps can be reused by each subsequent layer. Inspired by an image caption, a person attribute recognition network is proposed based on long-short-term memory network and attention mechanism. By fusing identification results of MiF-CNN and attribute recognition, this paper introduces the attribute-aided reranking algorithm to improve the accuracy of person re-id further. Experiments on VIPeR, CUHK01, and Market1501 datasets verify the proposed MiF-CNN can be trained sufficiently with small-scale datasets and obtain outstanding accuracy of person re-id. Contrast experiments also confirm the availability of the attribute-assisted reranking algorithm.
Abstract.A feature extraction method of palmprint recognition based on TwoDimensional Principal Component Analysis (2DPCA) is proposed in this work. A series of experiments were performed on the PolyU-Online-Palmprint -Database with a nearest neighbor classifier and cosine distance. The recognition rate is 99.14%. The 2DPCA method has more recognition accuracy and more computationally efficient than PCA, especially in the small training samples. At the same time the selection of threshold has been researched in different application systems.
The complex environment background, lighting conditions, and other action-irrelevant visual information in the video frame bring a lot of redundancy and noise to the action spatial features, which seriously affects the accuracy of action recognition. Aiming at this point, we propose a recurrent region attention cell to capture the action-relevant regional visual information in the spatial feature, and according to the temporal sequential natures of the video, on the basis of the recurrent region attention cell, a Recurrent Region Attention model (RRA) is proposed. The recurrent region attention cell in the RRA iterates according to the temporal sequence of the video, so that the attention performance of the RRA is gradually improved. Secondly, we propose a Video Frame Attention model (VFA) that can highlight the more important frames in the whole action video sequence, so as to reduce the interference caused by the similarity between the heterogeneous action video sequences. Finally, we propose an end-to-end trainable network: Two-level Attention Model based video action recognition network (TAMNet). We experimented on two video action recognition benchmark datasets: UCF101 and HMDB51. Experiments show that our end-to-end TAMNet network can reliably focus on the more important video frames in the video sequence, and effectively capture the action-relevant regional visual information in the spatial features of each frame of the video sequence. Inspired by the two-stream structure, we construct a two-modalities TAMNet network. In the same training conditions, the two-modalities TAMNet network achieved optimal performance on both datasets.
With reference to the common vehicle abnormal behaviors, the article presents a video-based vehicle abnormal behavior detection system. On the basis of background subtraction methods to detect vehicles, the vehicle tracking and abnormal behavior identification was realized by building up information chain of tracked vehicles. The system solves effectively the problems of traditional method, such as losing detection and wrong matching. The experiments showed that the system could not only detect vehicle abnormal behavior correctly, but also calculate the traffic flow and count the number of vehicles which broke traffic rules accurately.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.