Open AccessPyTorch YOLOv3 Object Detection for Vehicle Identification
Author(s) -
Mohith Rajendra,
Shreya Shridhar
Publication year - 2020
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.e1007.0285s20
Subject(s) - artificial intelligence , computer science , computer vision , object detection , training set , transfer of learning , set (abstract data type) , classifier (uml) , deep learning , task (project management) , pattern recognition (psychology) , management , economics , programming language
Detecting real-world vehicle objects captured from car-mounted cameras requires manual labelling of video images. Previous vehicle object detection papers such as the winners of the 2018 AI City Challenge [1] used a training set of over 4,500 hand labelled images. In this paper, we attempt to automate this task by applying transfer learning to a YOLOv3 model trained on Imagenet and then re-trained on a set of stock car images and a small subset of hand labelled images taken from front-mounted dashboard camera videos. The mean Average Precision (mAP) of the validation set is used to determine the effectiveness of model vehicle classification. There is a significant variance issue between the validation and training set because the video images are taken in 1) various weather and lighting conditions and 2) the stock images have different image perspectives. The experimental results demonstrate that the YOLOv3 model can reach an overall 16.07% mAP after 60 epochs of training and can identify classes of vehicles that had few training examples in the dataset