Search

Application of Small Object Detection in Autonomous Driving Abstract

Author(s)

Zichun Tang

Affiliation(s)

Central South University, Changsha, Hunan, China

Abstract

This paper aims to provide a comprehensive review of the current application status and development trends of small object detection technology in the field of autonomous driving. With the rapid development of autonomous driving technology, small object detection, as a crucial part of environmental perception, is of great significance for improving the safety and reliability of autonomous driving systems. The article first introduces the definition, characteristics, and challenges of small object detection. Then, it elaborates on the deep-learning-based small object detection methods, mainly including data augmentation, multi-scale feature fusion, super-resolution, and context information utilization. Subsequently, the specific application scenarios of small object detection in autonomous driving, such as pedestrian, vehicle, and traffic sign detection, are explored. Finally, the existing challenges in current research are analyzed, and the future development directions are prospected, providing references for related research.

Keywords

Small Object Detection; Autonomous Driving; Deep Learning; Environmental Perception; Computer Vision

References

[1] Yin Fanqing, Li Chuanyou, Jiang Liangchao, et al. Development Status and Prospect of Autonomous Driving Vehicles [J]. Motorcycle Technology, 2018(11): 33 - 36. [2] Liu Ying, Liu Hongyan, Fan Jiulun, et al. Review of Research and Application of Small Object Detection Based on Deep Learning [J]. Acta Electronica Sinica, 2020, 48(03): 590 - 601. [3] Pan Xiaoying, Jia Ningxin, Mu Yuanzhen, et al. Review of Small Object Detection Research [J]. Journal of Image and Graphics, 2023, 28(09): 2587 - 2615. [4] Kisantal M ,Wojna Z ,Murawski J , et al.Augmentation for small object detection.[J].CoRR,2019,abs/1902.07296 [5] Bochkovskiy A， Wang C Y and Liao H Y M. 2020. Yolov4： Optimal speed and accuracy of object detection. Computer Vision and Pat‐tern Recognition [EB/OL]. [2020-04-23] [6] LIN T Y, DOLLÁR P, GIRSHICK R B, et al.Featurepyramid networks for object detection[C]//2017 IEEEConference on Computer Vision and Pattern Recognition（CVPR），2017：936-944. [7] Dong Gang, Xie Weicheng, Huang Xiaolong, et al. Review of Deep Learning - based Small Object Detection Algorithms [J]. Computer Engineering and Applications, 2023, 59(11): 16 - 27. [8] GUO C，FAN B，ZHANG Q，et al.AugFPN：improvingmulti- scale feature learning for object detection[C]//2020 IEEE/CVF Conference on Computer Vision andPattern Recognition（CVPR），2020：12592-12601. [9] LIU S，QI L，QIN H，et al.Path aggregation network forinstance segmentation[C]//2018 IEEE/CVF Conferenceon Computer Vision and Pattern Recognition，2018：8759-8768. [10] Liu S T， Huang D and Wang Y H. 2019. Learning spatial fusion for single-shot object detection. Computer Vision and Pattern Recognition [EB/OL]. [2019-11-25]. http://arxiv.org/pdf/1911.09516.pdf [11] Dong C ,Loy C C ,He K , et al.Image Super-Resolution Using Deep Convolutional Networks.[J].CoRR,2015,abs/1501.00092 [12] WENZHE SHI, JOSE CABALLERO, FERENC HUSZÁR, et al. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network[C]//29th IEEE Conference on Computer Vision and Pattern Recognition: 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 26 June – 1 July 2016, Las Vegas, Nevada.:Institute of Electrical and Electronics Engineers, 2016:1874-1883. [13] CHRISTIAN LEDIG, LUCAS THEIS, FERENC HUSZÁR, et al. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition: CVPR 2017, Honolulu, Hawaii, USA, 21-26 July 2017, pages 1-751, [v.1].:Institute of Electrical and Electronics Engineers, 2017:105-114. [14] Li Z , Zhou F .FSSD: Feature Fusion Single Shot Multibox Detector[J]. 2017. [15] Liu Kuan, Lang Lei. Research on Lightweight SSD Object Detection Method [J]. Journal of Hubei Minzu University (Natural Science Edition), 2021, 39(4): 418 - 424. [16] Luo Yan, Zhang Chongyang, Tian Yonghong, et al. Review of Deep - Learning - based Pedestrian Detection Methods [J]. Journal of Image and Graphics, 2022, 27(07): 2094 - 2111. [17] Liu S, Zhuang Y, Dong H, et al. Adaptive Local Context Embedding for Small Vehicle Detection from Aerial Optical Remote Sensing Images[C]//IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium, Hangzhou: IEEE, 2022: 1712-1715. [18] Zhu H, Chen X, Dai W, et al. Orientation robust object detection in aerial images using deep convolutional neural network[C]//2015 IEEE International Conference on Image Processing (ICIP), Quebec City: IEEE, 2015: 3735-3739. [19] Razakarivony S, Jurie F. Vehicle detection in aerial imagery: A small target detection benchmark[J]. Journal of Visual Communication and Image Representation, 2016, 34: 187-203.