Abstract
Many pieces of information are included in the front region of a vehicle, especially in windshield and bumper regions. Thus, windshield or bumper region detection is making sense to extract useful information. But the existing windshield and bumper detection methods based on traditional artificial features are not robust enough. Those features may become invalid in many real situations (e.g. occlude, illumination change, viewpoint change.). In this article, we propose a multi-attribute-guided vehicle discriminately region detection method based on convolutional neural network and not rely on bounding box regression. We separate the net into two branches, respectively, for identification (ID) and Model attributes training. Therefore, the feature spaces of different attributes become more independent. Additionally, we embed a self-attention block into our framework to improve the performance of local region detection. We train our model on PKU_VD data set which has a huge number of images inside. Furthermore, we labeled the handcrafted bounding boxes on 5000 randomly picked testing images, and 1020 of them are used for evaluation and 3980 as the training data for YOLOv3. We use Intersection over Union for quantitative evaluation. Experiments were conducted in three different latest convolutional neural network trunks to illustrate the detection performance of the proposed method. Simultaneously, in terms of quantitative evaluation, the performance of our method is close to YOLOv3 even without handcrafted bounding boxes.
Highlights
With the development of automation and intelligence, intelligent transportation systems and security surveillance systems are widely used in various fields
The information of vehicles is inevitably needed to process due to different requirements (e.g. vehicle model recognition,[1,2,3,4] vehicle re-identification (Re-ID) task,[5,6,7] license plate recognition,[8,9] occupant violations10–12)
The main contributions of our method are as follows: (1) We use a dual-branch CNN architecture adopt to the multi-attribute and train our model based on multi-attribute labels to obtain the attention map of different attributes in order to detect multi-local regions simultaneously
Summary
With the development of automation and intelligence, intelligent transportation systems and security surveillance systems are widely used in various fields. Fang et al.[2] generate the bumper region by the feature map-based location and consider the multi-grain information, they only pay attention to the bumper region for vehicle model recognition. (1) We use a dual-branch CNN architecture adopt to the multi-attribute and train our model based on multi-attribute labels to obtain the attention map of different attributes in order to detect multi-local regions simultaneously. The feature maps are generated from different attribute branches, and both feature maps are input into the proposed positioning method, so as to achieve adaptive acquisition of the bounding box. We will detail our method from four parts: dual-branch architecture, loss function, self-attention block, and the proposed position algorithm. By processing the heatmaps through the proposed positioning block, detection boxes corresponding to different attributes can be obtained.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
