Integrating big data, video annotation and cloud based technologies for improved ADAS and Digital Mapping
The automotive industry needs tools that can manage the extremely large volumes of data (Big Data) especially to provide support in the annotation task (ADAS, cartography market). One of the main bottlenecks in advancing in several application domains is the lack of labelled realistic video datasets of sufficient size, complexity and coverage (comprehensiveness).
The performance of computer vision or video analysis systems is inherently restricted by the quality of the available training data. Manually collating and annotating such datasets is:
and excessively costly
The Cloud LSVA Solution
We want to build a software platform to address the needs for annotation, recognition and fusion of video and vehicle data by building a software platform for efficient and collaborative semiautomatic labelling and exploitation of large-scale video data.
By making both the ADAS and the dynamic mapping sectors capable of handling large amount of data we will be able to:
- Create large training datasets of visual samples for training models to be used in vision-based detection.
- Generate ground truth scene descriptions based on objects and events to evaluate the performance of detective algorithms and systems
By automating or semi-automating the video annotation process we can bypass the human factor and open up the possibilities for video analytics triggered innovation in the automotive domain.
Cloud LSVA Objectives
Cloud-LSVA will analyse and decompose each recorded scene, in order to detect and classify relevant objects and events for specific scenarios. Furthermore, the mined and annotated video metadata shall be used to train and evaluate algorithms for real-time analysis of visual and non-visual sensors in cars. We will be testing the platform in 2 scenarios:
Analysis and annotation of petabytes of data to train and validate visual, radar and telemetry sensor data to create continuously improving ADAS algorithms for deployment in motor vehicles with possible applications in autonomous vehicles and robotics.
Street and lane level analysis and interpretation of video to automatically create new digital maps for navigation applications and provide assisted positioning (i.e. in urban canyons, underground parking structures, complex flyovers, tunnels) for deployment in motor vehicles with certain application in autonomous vehicles and robotics
The Cloud LSVA project will follow a 3 step approach to provide video annotation standards:
1. Use an open group to develop the video annotation standards
2. Liaise with a Standard Development Organization to publish the resulting standards
3. Carry out open TestFest events to validate the standards