Person tracking using motion detection and optical flow

Person tracking systems to date have either relied on motion detection or optical flow as a basis for person detection and tracking. As yet, systems have not been developed that utilise both these techniques. We propose a person tracking system that uses both, made possible by a novel hybrid optical flow-motion detection technique that we have developed. This provides the system with two methods of person detection, helping to avoid missed detections and the need to predict position, which can lead to errors in tracking and mistakes when handling occlusion situations. Our results show that our system is able to track people accurately, with an average error less than four pixels, and that our system outperforms the current CAVIAR benchmark system.

Adaptive optical flow for person tracking

Person tracking systems are dependent on being able to locate a person accurately across a series of frames. Optical flow can be used to segment a moving object from a scene, provided the expected velocity of the moving object is known; but successful detection also relies on being able segment the background. A problem with existing optical flow techniques is that they don’t discriminate the foreground from the background, and so often detect motion (and thus the object) in the background. To overcome this problem, we propose a new optical flow technique, that is based upon an adaptive background segmentation technique, which only determines optical flow in regions of motion. This technique has been developed with a view to being used in surveillance systems, and our testing shows that for this application it is more effective than other standard optical flow techniques.

Stretching-induced orientation to improve mechanical properties of electrospun pan nanocomposites

Partially aligned and oriented polyacrylonitrile(PAN)-based nanofibers were electrospun from PAN and SWNTs/PAN in the solution of dimethylformamide(DMF) to make the carbon nanofibers. The as-spun nanofibers were hot-stretched in an oven to enhance its orientation and crystallinity. Then it were stabilized at 250 square under a stretched stress, and carbonized at 1000 square in N-2 atmosphere by fixing the length of the stabilized nanofiber to convert them into carbon nanofibers. With this hot-stretched process and with the introduction of SWNTs, the mechanical properties will be enhanced correspondingly. The crystallinity of the stretched fibers confirmed by X-ray diffraction has also increased. For PAN nanofibers, the improved fiber alignment and crystallinity resulted in the increased mechanical properties, such as the modulus and tensile strength of the nanofibers. It was concluded that the hot-stretched nanofiber and the SWNTs/PAN nanofibers can be used as a potential precursor to produce high-performance carbon composites.

Improving daylighting performance of mirrored light pipes

This paper assesses and compares the performances of two daylight collection strategies, one passive and one active, for large-scale mirrored light pipes (MLP) illuminating deep plan buildings. Both strategies use laser cut panels (LCP) as the main component of the collection system. The passive system comprises LCPs in pyramid form, whereas the active system uses a tiled LCP on a simple rotation mechanism that rotates 360° in 24 hours. Performance is assessed using scale model testing under sunny sky conditions and mathematical modelling. Results show average illuminance levels for the pyramid LCP ranging from 50 to 250 lux and 150 to 200 lux for the rotating LCPs. Both systems improve the performance of a MLP. The pyramid LCP increases the performance of a MLP by 2.5 times and the rotating LCP by 5 times, when compared to an open pipe particularly for low sun elevation angles.