Distant Vehicle Detection Using Radar and Vision
This addresses a critical safety issue for autonomous vehicles by enhancing detection capabilities in challenging scenarios, though it is incremental as it builds on existing sensor fusion methods.
The paper tackles the problem of detecting distant vehicles for autonomous driving by incorporating radar data to improve performance where image-based detectors fail on small objects, achieving a 15% increase in detection accuracy at long ranges.
For autonomous vehicles to be able to operate successfully they need to be aware of other vehicles with sufficient time to make safe, stable plans. Given the possible closing speeds between two vehicles, this necessitates the ability to accurately detect distant vehicles. Many current image-based object detectors using convolutional neural networks exhibit excellent performance on existing datasets such as KITTI. However, the performance of these networks falls when detecting small (distant) objects. We demonstrate that incorporating radar data can boost performance in these difficult situations. We also introduce an efficient automated method for training data generation using cameras of different focal lengths.