Radar Object Detection

CRUW is a dataset for the radar object detection (ROD) task, which aims to classify and localize the objects in 3D purely from radar's radio frequency (RF) images. The CRUW dataset has a systematic annotation and evaluation system, which involves camera RGB images and radar RF images, collected in various driving scenarios.

BAAI-VANJEE is a dataset for benchmarking and training various computer vision tasks such as 2D/3D object detection and multi-sensor fusion. The BAAI-VANJEE roadside dataset consists of LiDAR data and RGB images collected by VANJEE smart base station placed on the roadside about 4.5m high. This dataset contains 2500 frames of LiDAR data, 5000 frames of RGB images, including 20% collected at the same time. It also contains 12 classes of objects, 74K 3D object annotations and 105K 2D object annotations.

The RaDelft dataset is a novel, large-scale, real-life, and multi-sensor dataset that has been recorded using a demonstrator vehicle in different locations in the city of Delft. It contains data from a lidar, an imaging radar board, a camera, and the ego vehicle’s odometry. Check the reference paper for more details about the data collection and the sensors' setup. To request access, use the following link: https://docs.google.com/forms/d/1whyNTiAsZ4l0ENwFiut4yb3FzF3yPjKCdH42OMTlaEk/