Adaptive Space-Time Structural Coherence for Selective Imaging

David Gibson, Neill Campbell

Research output: Contribution to conferenceConference Paperpeer-review

353 Downloads (Pure)


In this paper we present a novel, low size, weight and power, close-to-sensor computational camera design. The hardware can be configured for a wide range of autonomous applications such as industrial inspection, binocular/stereo robotic vision, UAV navigation/control and biological vision analogues. Close coupling of the image sensor with computation, motor control and motion sensors enables low latency responses to changes in the visual field. An image processing pipeline that detects and processes regions containing space-time structural coherence, in order to reduce the transmission of redundant pixel data and stabilise selective imaging, is introduced. The pipeline is designed to exploit close-to-sensor processing of regions-of-interest (ROI) adaptively captured at high temporal rates (up to 1000 ROI/s) and at multiple spatial and temporal resolutions. Space-time structurally coherent macro blocks are detected using a novel temporal block matching approach; the high temporal sampling rate allows a monotonicity constraint to be enforced to efficiently assess confidence of matches. The robustness of the sparse motion estimation approach is demonstrated in comparison to a state-of-the-art optical flow algorithm and optimal Baysian grid-based filtering. A description of how the system can generate unsupervised training data for higher level multiple instance or deep learning systems is discussed.
Original languageEnglish
Publication statusPublished - 27 Sept 2017
EventDesign and Architectures for Signal and Image Processing (DASIP2017) - Dresden, Germany
Duration: 27 Sept 201729 Sept 2017


ConferenceDesign and Architectures for Signal and Image Processing (DASIP2017)
Internet address


  • Close-to-sensor processing
  • feature analysis
  • low latency processing
  • sub-pixel tracking


Dive into the research topics of 'Adaptive Space-Time Structural Coherence for Selective Imaging'. Together they form a unique fingerprint.

Cite this