Vehicle detection based on improved multitask cascaded convolutional neural network and mixed image enhancement. Issue 17 (8th March 2021)

• Record Type: Journal Article
• Authors: Xu, Ke; Gong, Hua; Liu, Fang
• Is Part Of: IET image processing. Volume 14:Issue 17(2020)
• Page Start: 4621
• Page End: 4632
• Publication Date: 2021-03-08
• Subjects: feature extraction -- image enhancement -- image segmentation -- data mining -- learning (artificial intelligence) -- fuzzy set theory -- object detection -- image classification -- image colour analysis -- traffic engineering computing -- neural nets; lightweight convolutional neural network -- convolutional layers -- fuzzy objects -- network training -- COCO‐Vehicle dataset -- Vehicle detection -- improved multitask -- mixed image enhancement -- detection effect -- fuzzy vehicles -- size vehicles -- IMC‐CNN -- image blurring -- imaging environment -- object location network -- multilayer feature fusion -- single vehicle object -- object classification network; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.1005
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : In order to increase the detection effect of fuzzy vehicles and small size vehicles, an improved multitask cascaded convolutional neural network (IMC‐CNN) based on mixed image enhancement is proposed. Firstly, contrast limited adaptive histogram equalisation and multi‐scale Retinex are used to enhance images. Mixed image enhancement can effectively solve the problems of image blurring, low contrast and uneven illumination when the imaging environment is not ideal. IMC‐CNN includes two stages: object location and object classification. The object location network based on multi‐layer feature fusion can locate and extract the object from complex background, and output regions contain only a single vehicle object. The object classification network is a lightweight convolutional neural network with only two convolutional layers, which can effectively reduce information loss and improve the classification accuracy of small objects and fuzzy objects. In addition, online hard example mining algorithm and focal loss function are adopted in network training. These strategies can solve the problem of unbalance between positive and negative samples. To verify the validity of the proposed algorithm, the experiments are performed on SYIT‐Fuzzy dataset and COCO‐Vehicle dataset. Compared with Faster R‐CNN, YOLO v4 and other recent models, the average classification accuracy of the proposed method is significantly increased.