Autonomous Object Detection


This project initially started as a code base for this hackathon. This is a winning entry (team B) on the leaderboard. It later was transformed into a common project for object detection for autonomous driving. It later was also used for ICCVW 2019 (AutoNUE) paper. The code is publicly available at this Github URL.

This work provides support for the following datasets (related to object detection for autonomous navigation):

These Dataset class complies with torchvision API. Users can create their own Dataset class if they want to use some other dataset. By default, FasterRCNN is loaded to perform the training and evaluation is performed in the same way as MS-COCO format.