IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector
This work addresses object detection for autonomous driving systems, but it is incremental as it combines existing techniques like ResNet-18 FPN and Cascade R-CNN.
The paper tackled the problem of detecting on-road objects under varying lighting conditions by using subclass separation, sample skipping, and external training data, achieving improved detection accuracy on the Nvidia Jetson TX2 platform.
It is hard to detect on-road objects under various lighting conditions. To improve the quality of the classifier, three techniques are used. We define subclasses to separate daytime and nighttime samples. Then we skip similar samples in the training set to prevent overfitting. With the help of the outside training samples, the detection accuracy is also improved. To detect objects in an edge device, Nvidia Jetson TX2 platform, we exert the lightweight model ResNet-18 FPN as the backbone feature extractor. The FPN (Feature Pyramid Network) generates good features for detecting objects over various scales. With Cascade R-CNN technique, the bounding boxes are iteratively refined for better results.