Skip to main content

LOCUST

Life-like object detection for collision avoidance using spatiotemporal image processing

The work is structured into 6 Work Packages. WP1 to WP4 embrace the technical work, while WP0 is dedicated to management and quality assurance, and WP5 to dissemination and exploitation plans.

In particular, the work packages are the following: WP0: Project Management and Quality Assurance; WP1: Biological Modelling and Model Customisation; WP2: System Architecture and Hardware/Software Integration; WP3: Bio-Inspired Sensory-Processing Application-Specific Integrated Circuits; WP4: System requirements and Demonstrator; WP5: Dissemination and Exploitation. WP1 is devoted to the modelling of the biological circuitry using both physiological and computational tools to extract thw unique features of the locust neuro-vision system. Similar models from other insects perception systems will be analysed and their general characteristics will be explored. This task is led by experts in neuro-biology. WP2, led by an opto-electornics information-technology expert embraces work in the fields of modelling and implementation from a systems perspective. Activities here are aimed to determine an optimum architecture and partitioning of artificial vision systems on a chip. WP3, led by mixed-signal IC design experts, is devoted to defining suitable Vision System on Chip (VSoC) architectures, exploring the different trade-offs asociated to their implementation, addressing all pertinent robustness issues, and finally designing a particular VSoC test proptotype for the application of collision-threat warning in automobiles. WP4, led by an automobile manufacturing company, is devoted to the definition of the specific system requirements, embedding it in a car, and evaluating the resulting real-life demonstrator. In addition to the specific demonstrator, the consortium will dedicate substantial efforts to producing general design techniques, valid for any similar application-specific VSoC.

Expected results:

Expected results comprise substantial scientific and technical advances at different levels of knowledge (neuro-biology, information technology, hardware/software co-design, mixed-signal sensory/processing chip design) with generic value for the realization of bio-inspired Vision Systems on Chip. On the other hand, a specific demonstrator for collision avoidance in the automotive field will be fabricated and tested under real-world conditions.