Abstract
Pedestrian attributes (such as gender, age, hairstyle, and clothing) can effectively represent the appearance of pedestrians. These are high-level semantic features that are robust to illumination, deformation, etc. Therefore, they can be widely used in person re-identification, video structuring analysis and other applications. In this paper, a pedestrian attributes recognition method for surveillance scenarios using a multi-task lightweight convolutional neural network is proposed. Firstly, the labels of the attributes for each pedestrian image are integrated into a label vector. Then, a multi-task lightweight Convolutional Neural Network (CNN) is designed, which consists of five convolutional layers, three pooling layers and two fully connected layers to extract the deep features of pedestrian images. Considering that the data distribution of the datasets is unbalanced, the loss function is improved based on the sigmoid cross-entropy, and the scale factor is added to balance the amount of various attributes data. Through training the network, the mapping relationship model between the deep features of pedestrian images and the integration label vector of their attributes is established, which can be used to predict each attribute of the pedestrian. The experiments were conducted on two public pedestrian attributes datasets in surveillance scenarios, namely PETA and RAP. The results show that, compared with the state-of-the-art pedestrian attributes recognition methods, the proposed method can achieve a superior accuracy by 91.88% on PETA and 87.44% on RAP respectively.
Highlights
People often identify a person through discrete and precise attributes such as clothing style, gender, weight, and hairstyle
The results show that, compared with the state-of-the-art pedestrian attributes recognition methods, the proposed method can achieve a superior accuracy by 91.88% on PETA and 87.44% on Keywords: pedestrian attributes recognition; lightweight convolutional neural network; multi-task; surveillance scenarios
On the public pedestrian attribute dataset PETA, the mean recognition accuracy of the proposed method is as high as 91.88%, and is Considering the intrinsic relationship among the pedestrian attributes, the recognition task of pedestrian attributes can be completed in a unified framework
Summary
People often identify a person through discrete and precise attributes such as clothing style, gender, weight, and hairstyle. Attributes are types of high-level semantic features. Compared with low-level visual features, attributes are complex in terms of extraction and expression. It requires a lot of cost, labor and time to label the attributes, but they contain more abundant semantic information and have stronger robustness to illumination and angle changes. The attributes can be exploited to finely characterize the appearance of pedestrians from multiple different aspects. They have important value in the applications of person re-identification, video structuring analysis, etc
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
