Vehicles Detection Using Deep Learning With Improved Single Shot Detector

Abstract

Training datasets manually with a variety of car models’ images would be time consuming due to the huge datasets. Hence, mobilenet V2 network architecture is implemented on existing single shot detector (SSD) network to improve the detection accuracy (mean average precision, mAP), inference time and sensitivity towards small objects in complex backgrounds without increasing the computation complexity. The transfer learning mechanism for the custom dataset is applied to increase detection accuracy against small objects and reduce training time. Custom datasets are used for training and testing, where the datasets are annotated using labelImg. Google Colab and some open-source libraries, Tensorflow and Keras are used in model training. The performance of improved-SSD in object detection is evaluated based on inference time and mean average precision (mAP). All models are pretrained using Common Objects in Context dataset (COCO). Based on the result obtained, 1.76 seconds needed for Faster R-CNN model to perform inference per image whereas 1.24 seconds needed for proposed model to perform the same tasks. The inference time of proposed model is approximate 30% faster than the Faster R-CNN model. The mean average precision of the proposed model is 73.4% whereas the average recall rate of the proposed model is 80%. Besides, the proposed model obtains approximately 10% improvement in terms of mAP detecting small object if compared with Faster R-CNN model. The proposed model able to detect vehicles with shorter inference time and good accuracy.