RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking
This addresses a dataset deficiency problem for researchers in RGB-D object tracking, enabling better exploitation of depth channels, though it is incremental as it builds on existing tracking methods.
The authors tackled the lack of large-scale annotated RGB-D data for object tracking by releasing the RGBD1K dataset with 1,050 sequences and 2.5M frames, and demonstrated its potential by developing a transformer-based tracker that improves performance.
RGB-D object tracking has attracted considerable attention recently, achieving promising performance thanks to the symbiosis between visual and depth channels. However, given a limited amount of annotated RGB-D tracking data, most state-of-the-art RGB-D trackers are simple extensions of high-performance RGB-only trackers, without fully exploiting the underlying potential of the depth channel in the offline training stage. To address the dataset deficiency issue, a new RGB-D dataset named RGBD1K is released in this paper. The RGBD1K contains 1,050 sequences with about 2.5M frames in total. To demonstrate the benefits of training on a larger RGB-D data set in general, and RGBD1K in particular, we develop a transformer-based RGB-D tracker, named SPT, as a baseline for future visual object tracking studies using the new dataset. The results, of extensive experiments using the SPT tracker emonstrate the potential of the RGBD1K dataset to improve the performance of RGB-D tracking, inspiring future developments of effective tracker designs. The dataset and codes will be available on the project homepage: https://github.com/xuefeng-zhu5/RGBD1K.