A Nighttime Vehicle Detection Method with Attentive GAN for Accurate Classification and Regression
Open Access
Abstract
Vehicle detection plays a vital role in the design of Automatic Driving System (ADS), which has achieved remarkable improvements in recent years. However, vehicle detection in night scenes still has considerable challenges for the reason that the vehicle features are not obvious and are easily affected by complex road lighting or lights from vehicles. In this paper, a high-accuracy vehicle detection algorithm is proposed to detect vehicles in night scenes. Firstly, an improved Generative Adversarial Network (GAN), named Attentive GAN, is used to enhance the vehicle features of nighttime images. Then, with the purpose of achieving a higher detection accuracy, a multiple local regression is employed in the regression branch, which predicts multiple bounding box offsets. An improved Region of Interest (RoI) pooling method is used to get distinguishing features in a classification branch based on Faster Region-based Convolutional Neural Network (R-CNN). Cross entropy loss is introduced to improve the accuracy of classification branch. The proposed method is examined with the proposed dataset, which is composed of the selected nighttime images from BDD-100k dataset (Berkeley Diverse Driving Database, including 100,000 images). Compared with a series of state-of-the-art detectors, the experiments demonstrate that the proposed algorithm can effectively contribute to vehicle detection accuracy in nighttime.Keywords
Funding Information
- National Natural Science Foundation of China (61605175)
This publication has 49 references indexed in Scilit:
- Research on highway vehicle detection based on faster R-CNN and domain adaptationApplied Intelligence, 2021
- A lightweight Tiny-YOLOv3 vehicle detection approachJournal of Real-Time Image Processing, 2021
- On-road vehicle detection in varying weather conditions using faster R-CNN with several region proposal networksMultimedia Tools and Applications, 2021
- Real-time object detection based on YOLO-v2 for tiny vehicle objectProcedia Computer Science, 2021
- Vehicle Detection and Classification: A Review2020
- Underwater image enhancement using improved generative adversarial networkConcurrency and Computation: Practice and Experience, 2020
- Inception-SSD: An improved single shot detector for vehicle detectionJournal of Ambient Intelligence and Humanized Computing, 2020
- RETRACTED ARTICLE: An intelligent multiple vehicle detection and tracking using modified vibe algorithm and deep learning algorithmSoft Computing, 2020
- Towards accurate tiny vehicle detection in complex scenesNeurocomputing, 2019
- Extreme learning machine: Theory and applicationsNeurocomputing, 2006