Exploiting Temporal Context for Tiny Object Detection

In surveillance applications, the detection of tiny, lowresolution objects remains a challenging task. Most deep learning object detection methods rely on appearance features extracted from still images and struggle to accurately detect tiny objects. In this paper, we address the problem of tiny object detection for real-time surveillance...

Turbulence mitigation in imagery including moving objects from a static event camera

Long-range horizontal path imaging through atmospheric turbulence is hampered by spatiotemporally randomly varying shifting and blurring of scene points in recorded imagery. Although existing software-based mitigation strategies can produce sharp and stable imagery of static scenes, it remains highly challenging to mitigate turbulence in scenes...

Turbulence mitigation in neuromorphic camera imagery

Onboard ROI selection for aerial surveillance using a high resolution, high framerate camera

With the latest advances in image sensor technology, cameras are able to generate video with tens of megapixels per frame. These high resolution videos streams offer great potential to be used in the surveillance domain. For ground based systems, gigapixel streams are already used with great effect as illustrated by the ICME 2019 crowd counting...

Using event cameras for imaging through atmospheric turbulence

Long range horizontal path imaging through atmospheric turbulence is hampered by spatiotemporally randomly varying shifting and blurring of scene points in recorded imagery. Typical mitigation strategies employ software algorithms that combine optical flow to estimate and reduce tip/tilt aberrations with lucky patch identification and data...