Active Structured Learning for High-Speed Object Detection
Christoph Lampert and Jan Peters
In: Symposium of the German Association for Pattern Recognition (DAGM), Jena(2009).
High-speed smooth and accurate visual tracking of objects in arbitrary, unstructured environments is essential for robotics and human motion analysis. However, building a system that can adapt to arbitrary objects and a wide range of lighting conditions is a challenging problem, especially if hard real-time constraints apply like in robotics scenarios. In this work, we introduce a method for learning a discriminative object tracking system based on the recent structured regression framework for object localization. Using a kernel function that allows fast evaluation on the GPU, the resulting system can process video streams at speed of 100 frames per second or more.
Consecutive frames in such high framerate sequences are typically very redundant, and for training an object detection system, it is sufficient to have training labels from only a subset of all images. We propose an active learning method that select training examples to be labeled in a data-driven way, thereby minimizing the required number of training labeling. This is of specific importance, because labeling the position of an object an image to the pixel level requires significant manual effort. Experiments on realistic data show that the active learning is superior to previously used methods for dataset subsampling for this task.