Report on UG2+ challenge Track 1: Assessing algorithms to improve video object detection and classification from unconstrained mobility platforms

Sreya Banerjee, Rosaura G. VidalMata, Zhangyang Wang, Walter J. Scheirer

Abstract: Highlights•A new benchmark dataset to evaluate object detection and classification of videos taken in the wild via unmanned aerial vehicles and gliders, as well as by a controlled collection on the ground.•Novel evaluation methods and metrics for image restoration and enhancement algorithms, with a particular emphasis on no-reference metrics, since for most real outdoor images with adverse visual conditions it is hard to obtain any clean “ground truth” to compare with.•A summary of Track 1 of the UG2+<math><mrow is="true"><msup is="true"><mrow is="true"></mrow><mrow is="true"><mn is="true">2</mn></mrow></msup><mo is="true">+</mo></mrow></math> Challenge held at IEEE/CVF CVPR 2019, including the new dataset, evaluation procedures, extensive analysis on the submitted algorithms for explaining, quantifying, and optimizing the mutual influence of low-level computational photography tasks (image reconstruction, restoration, enhancement) and various high-level computer vision tasks.

External IDs:dblp:journals/cviu/BanerjeeVWS21