Abstract
Small obstacles can cause big accidents, even if the vehicle is equipped with an intelligent auxiliary system. In order to detect four kinds of small obstacles quickly and accurately, this paper proposes an optimized neural network algorithm based on YOLOv3. K-Means+ is used to determine the prior box and enhance the adaptability of the YOLO scale. For the data samples imbalance, loss function of YOLO is improved to increase the precision of the prediction box. In addition, a special classification and counting algorithm is proposed to get results quickly and visually. The experimental results show that the our method can classify and locate four kinds of small obstacles more accurately and faster.
Similar content being viewed by others
References
Aziz S, Youssef F et al (2018) Traffic sign recognition based on multi-feature fusion and elm classifier. Procedia Computer Science 127:146–153
Bazzi A, Kassem Z, Rahal M, Ghareeb M (2017) Uni-bus assist: A smarter safer bus. In: 2017 Sensors networks smart and emerging technologies (SENSET). IEEE, pp 1–4
Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv:2004.10934
Chen B, Miao X (2020) Distribution line pole detection and counting based on yolo using uav inspection line video. J Electric Eng Technol 15(1):441–448
Choi J, Chun D, Kim H, Lee HJ (2020) Gaussian yolov3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: 2019 IEEE/CVF International conference on computer vision (ICCV)
Feng ZH, Kittler J, Wu XJ (2019) Mining hard augmented samples for robust facial landmark localization with cnns. IEEE Signal Processing Letters 26 (3):450–454
Gu X, Cai Q, Lee J, Xiang Q, Ma Y, Xu X (2020) Proactive crash risk prediction modeling for merging assistance system at interchange merging areas. Traffic Injury Prevention 21(3):234–240
Ibrahim A, Tharwat A, Gaber T, Hassanien AE (2018) Optimized superpixel and adaboost classifier for human thermal face recognition. SIViP 12 (4):711–719
Körez A, Barışçı N (2020) Object detection with low capacity gpu systems using improved faster r-cnn. Appl Sci 10(1):83
Lakshmi MA, Daniel GV, Rao DS (2019) Initial centroids for k-means using nearest neighbors and feature means. In: Soft computing and signal processing. Springer, pp 27–34
Li F, Fan Y, Zhang X, Wang C, Hu F, Jia W, Hui H (2020) Multi-feature fusion method based on eeg signal and its application in stroke classification. J Med Syst 44(2):39
Lin T, Goyal P, Girshick R, He K, Dollár P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318–327
Liu M, Wang X, Zhou A, Fu X, Ma Y, Piao C (2020) Uav-yolo: Small object detection on unmanned aerial vehicle perspective. Sensors 20 (8):2238
Liu P, Yu H, Cang S (2019) Adaptive neural network tracking control for underactuated systems with matched and mismatched disturbances. Nonlinear Dynamics 98(2):1447–1464
Luo J, Yan B, Wood K (2017) Innogps for data-driven exploration of design opportunities and directions: The case of google driverless car project. Journal of Mechanical Design 139(11):111,416
Perrine KA, Kockelman KM, Huang Y (2020) Anticipating long-distance travel shifts due to self-driving vehicles. J Transp Geogr 82(102):547
Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv:1804.02767
Shi P, Qi Q, Qin Y, Scott PJ, Jiang X (2020) Intersecting machining feature localization and recognition via single shot multibox detector. IEEE Transactions on Industrial Informatics 17(5):3292–3302
Shit RC (2020) Crowd intelligence for sustainable futuristic intelligent transportation system: a review. IET Intell Transp Syst 14(6):480–494
Sun L, Zhao C, Yan Z, Liu P, Duckett T, Stolkin R (2018) A novel weakly-supervised approach for rgb-d-based nuclear waste object detection and categorization. IEEE Sensors J 19(9):3487–3500
Sun S, Petropulu AP, Poor HV (2020) Mimo radar for advanced driver-assistance systems and autonomous driving: Advantages and challenges. IEEE Signal Proc Mag 37(4):98–117
Weon IS, Lee SG, Ryu JK (2020) Object recognition based interpolation with 3d lidar and vision for autonomous driving of an intelligent vehicle. IEEE Access 8:65,599–65,608
Ye XY, Hong DS, Chen HH, Hsiao PY, Fu LC (2020) A two-stage real-time yolov2-based road marking detector with lightweight spatial transformation-invariant classification. Image Vis Comput 102(103):978
Zhou L, Min W, Lin D, Han Q, Liu R (2020) Detecting motion blurred vehicle logo in iov using filter-deblurgan and vl-yolo. IEEE Trans Veh Technol 69(4):3604–3614
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, B., Yang, X. Small obstacles image detection and classification for driver assistance. Multimed Tools Appl 81, 30785–30795 (2022). https://doi.org/10.1007/s11042-022-12706-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12706-5