Analysis of Pothole Detection Accuracy of Selected Object Detection Models Under Adverse Conditions

被引:0
|
作者
Frnda, Jaroslav [1 ]
Bandyopadhyay, Srijita [2 ]
Pavlicko, Michal [1 ]
Durica, Marek [1 ]
Savrasovs, Mihails [3 ]
Banerjee, Soumen [4 ]
机构
[1] Univ Zilina, Fac Operat & Econ Transport & Commun, Dept Quantitat Methods & Econ Informat, Univ 8215-1, Zilina 01026, Slovakia
[2] Univ Area Act Area 3, New Town 700160, W Bengal, India
[3] Transport & Telecommun Inst, Lomonosova 1, LV-1019 Riga, Latvia
[4] Narula Inst Technol, 81 Nilgunj Rd, Kolkata 700109, W Bengal, India
关键词
Computer vision; object detection; potholes; YOLOv7; FRCNN;
D O I
10.2478/ttj-2024-0016
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
Potholes detection is an essential aspect of road safety and road infrastructure maintenance. Potholes, which are typically caused by a combination of heavy traffic and weather, are depressions or holes in the road surface that can cause damage to specific parts of a vehicle. Autonomous vehicles, in particular, must be capable of detecting and avoiding them. Hitting a deep or sharp-edged pothole at high speed can lead to loss of control or even an accident. This makes pothole detection all the more important. The accuracy of pothole detection systems installed in autonomous vehicles may be significantly impaired by adverse weather and bad light conditions. Therefore, the classification accuracy of selected well-known computer vision models for pothole detection under these specific conditions has been investigated. The results were then compared with state-of-the-art methods. Our findings showed that we outperformed many of them when used under adverse weather and low light situations. This paper presents valuable insights into the precision of various computer vision models for potholes detection. It may aid in selecting the optimal model for a specific application.
引用
收藏
页码:209 / 217
页数:9
相关论文
共 50 条
  • [31] Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions
    Pfeuffer, Andreas
    Dietmayer, Klaus
    2018 21ST INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2018, : 2588 - 2595
  • [32] Multiple Adverse Weather Conditions Adaptation for Object Detection via Causal Intervention
    Zhang, Hua
    Xiao, Liqiang
    Cao, Xiaochun
    Foroosh, Hassan
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (03) : 1742 - 1756
  • [33] Low-light DEtection TRansformer (LDETR): object detection in low-light and adverse weather conditions
    Tiwari A.K.
    Pattanaik M.
    Sharma G.K.
    Multimedia Tools and Applications, 2024, 83 (36) : 84231 - 84248
  • [34] Mixture Models for Object Detection
    Kuang, Xiaoqin
    Sang, Nong
    Chen, Feifei
    Gao, Changxin
    Wang, Runmin
    COMPUTER VISION, CCCV 2015, PT I, 2015, 546 : 317 - 324
  • [35] Multiresolution Models for Object Detection
    Park, Dennis
    Ramanan, Deva
    Fowlkes, Charless
    COMPUTER VISION-ECCV 2010, PT IV, 2010, 6314 : 241 - 254
  • [36] A Review: Object Detection Models
    Shetty, Aakash K.
    Saha, Ishani
    Sanghvi, Rutvik M.
    Save, Siddhesh A.
    Patel, Yashkumar J.
    2021 6TH INTERNATIONAL CONFERENCE FOR CONVERGENCE IN TECHNOLOGY (I2CT), 2021,
  • [37] Yolov4-based hybrid feature enhancement network with robust object detection under adverse weather conditions
    Patil, Shankar M.
    Pawar, Shivaji D.
    Mhatre, Sonali N.
    Kharade, Prakash A.
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (05) : 4243 - 4258
  • [38] An Adaptive Prefiltering Method to Improve the Speed/Accuracy Tradeoff of Voltage Sequence Detection Methods Under Adverse Grid Conditions
    Matas, Jose
    Castilla, Miguel
    Miret, Jaume
    Garcia de Vicuna, Luis
    Guzman, Ramon
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2014, 61 (05) : 2139 - 2151
  • [39] LANE DETECTION UNDER ADVERSE CONDITIONS BASED ON DUAL COLOR SPACE
    Zarbakht, Nima
    Zou, Ju Jia
    2018 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA), 2018, : 179 - 183
  • [40] Traffic Sign Detection Under Adverse Environmental Conditions Based on CNN
    Gao, Qiang
    Hu, Huiping
    Liu, Wei
    IEEE ACCESS, 2024, 12 : 117572 - 117580