ICVGIP 2020 presents two new data challenges on Computer Vision and Machine learning

Recent progress in AI has revolutionized automatic visual perception, with many technologies now touching our daily lives. Two important and challenging Computer Vision problems: (i) Semantic Segmentation and (ii) Object Detection, are at the heart of many visual perception products. In ICVGIP 2020, we present two contests on these two tasks. The contest will for approximately 3 weeks with leaderboards constantly placing the competing teams relative to each other. The final winning teams will present their solutions at ICVGIP on December 20, 2020.

• Semantic Segmentation for Autonomous Driving

Computer vision based solutions are an important enabler for autonomous driving. A crucial module for scene understanding is to obtain a pixel-level semantic labeling of the images. This challenge will utilize the large-scale, public, India-centric dataset, India Driving Dataset (IDD) to evaluate the solutions provided by the competing teams. The instructions for participating in this challenge can be found here.

• Object Detection for Anti-Poaching Aerial Patrolling of Protected Areas

Computer Vision and Machine Learning has huge potential to change the society for good. We consider here the extremely relevant and important problem of mitigating poaching attacks on endangered animals in the wild. This challenge will utilize the BIRDSAI dataset for automatic detection of animals and humans in thermal IR aerial images collected from UAVs for augmenting anti-poaching patrols of protected areas. Solutions for automatic object detection are invited. Participating teams can download the training set from here.
The BIRDSAI track is hosted on EvalAI. Please participate at the BIRDSAI EvalAI page and submit your entries to the leaderboard.

Head here for the registration.

*Please keep checking this page for further updates and announcements regarding the contests.

Congratulations to the Winners