scene perception

Solving the external perception problem for autonomous vehicles and driver-assistance systems requires accurate and robust driving scene perception in both regularly-occurring driving scenarios (termed “common cases”) and rare outlier driving scenarios (termed “edge cases”). In order to develop and evaluate driving scene perception models at scale, and more importantly, covering potential edge cases from the real world, we take advantage of the MIT-AVT Clustered Driving Scene Dataset and build a subset for the semantic scene segmentation task.


Semantic scene segmentation has primarily been addressed by forming representations of single images both with supervised and unsupervised methods. The problem of semantic segmentation in dynamic scenes has begun to recently receive attention with video object segmentation approaches. What is not known is how much extra information the temporal dynamics of the visual scene carries that is complimentary to the information available in the individual frames of the video.