UG^2: a Video Benchmark for Assessing the Impact of Image Restoration and Enhancement on Automatic Visual Recognition

TL;DR

The UG^2 benchmark dataset enables assessment of how image restoration and enhancement techniques affect automatic visual recognition in challenging real-world video scenarios, highlighting the need for further algorithmic improvements.

Contribution

Introduces UG^2, a new benchmark dataset with annotated real-world videos for evaluating the impact of image processing on recognition accuracy.

Findings

Restoration techniques do not always improve recognition performance.

There is significant potential for developing better image enhancement algorithms.

Baseline experiments reveal room for innovation in image restoration for recognition tasks.

Abstract

Advances in image restoration and enhancement techniques have led to discussion about how such algorithmscan be applied as a pre-processing step to improve automatic visual recognition. In principle, techniques like deblurring and super-resolution should yield improvements by de-emphasizing noise and increasing signal in an input image. But the historically divergent goals of the computational photography and visual recognition communities have created a significant need for more work in this direction. To facilitate new research, we introduce a new benchmark dataset called UG^2, which contains three difficult real-world scenarios: uncontrolled videos taken by UAVs and manned gliders, as well as controlled videos taken on the ground. Over 160,000 annotated frames forhundreds of ImageNet classes are available, which are used for baseline experiments that assess the impact of known and unknown image artifacts and other conditions on common deep learning-based object classification approaches. Further, current image restoration and enhancement techniques are evaluated by determining whether or not theyimprove baseline classification performance. Results showthat there is plenty of room for algorithmic innovation, making this dataset a useful tool going forward.