Improvement of Large-Vehicle Detection and Monitoring on CPEC Route

Satellite imagery is being used to monitor agriculture fields, vehicle detection, surveillance and remote sensing. In this paper, we proposed large-vehicle detection to monitor the status on route of China Pakistan economic corridor (CPEC). In the present experiments, the region of interests extracted from more than thousand images through different angles to train machine for large-vehicle detection using RCNN, Fast-RCNN, Faster-RCCN and Cascade methods. The training images were enhanced through contrast change and image sharpening to avoid errors during detection of vehicles on route. Results show that the proposed method is promising for large-vehicle detection on CPEC route. The Faster-RCNN is more promising due to fast computational speed with high precision and recall rate. Furthermore, the developed dataset is also useful for future CPEC applications such as large-vehicles/trucks tracking, detection and identification. [GRAPHICS] .