Suchergebnisse

<p>Visual tracking is performed in a stabilised video. If the input video to the tracker algorithm is itself destabilised, incorrect motion vectors will cause a serious drift in tracking. Therefore video stabilisation is must before tracking. A novel algorithm is developed which simultaneously takes care of video stabilisation and target tracking. Target templates in just previous frame are stored in positive and negative repositories followed by Affine mapping. Then optimised affine parameters are used to stabilise the video. Target of interest in the next frame is approximated using linear combinations of previous target templates. Proposed modified L1 minimisation method is used to solve sparse representation of target in the target template subspace. Occlusion problem is minimised using the inherent energy of coefficients. Accurate tracking results have been obtained in destabilised videos.</p>

Camera zoom operation and fast approaching/receding target causes scaling of acquired target in video frames. Fast moving target manifests in large inter-frame motion. In general, non-uniform background degrades performance of tracking algorithms. Fast Fourier transform (FFT)-based Correlation algorithms improve tracking in this scenario, but their applications is limited to small inter-frame motion. Increasing search region has implication on execution speed of the algorithms. Rapid target scaling, non-uniform background and large inter-frame motion of target hinder accurate and long term visual tracking. These challenges have been addressed for extended target tracking by augmenting fast discriminative scale space tracking (fDSST) algorithm with probable target location prediction and target detection. Localisation of fast motion has been achieved by applying fused outputs of Kalman filter and quadratic regression based prediction before applying fDSST. It has helped in accurate localisation of fast motion without increasing search region. In each frame, target location and size have been estimated using fDSST and further refined by target detection near this location. Smoothing and limiting of trajectory and size of detected target has enhanced tracking performance. Experimental results show considerable improvement of precision, success rate and centre location error tracking performance against state-of-the-art trackers in stringent conditions.

A line-of-sight stabilised sighting system, capable of target tracking and video stabilisation is a prime requirement of any armoured fighting tank vehicle for military surveillance and weapon firing. Typically, such sighting systems have three prime electro-optical sensors i.e. day camera for viewing in day conditions, thermal camera for night viewing and eye-safe laser range finder for obtaining the target range. For laser guided missile firing, additional laser target designator may be a part of sighting system. This sighting system provides necessary parameters for the fire control computer to compute ballistic offsets to fire conventional ammunition or fire missile. System demands simultaneous interactions with electro-optical sensors, servo sensors, actuators, multi-function display for man-machine interface, fire control computer, logic controller and other sub-systems of tank. Therefore, a complex embedded electronics hardware is needed to respond in real time for such system. An efficient electronics embedded hardware architecture is presented here for the development of this type of sighting system. This hardware has been developed around SHARC 21369 processor and FPGA. A performance evaluation scheme is also presented for this sighting system based on the developed hardware.

A line-of-sight stabilised sighting system, capable of target tracking and video stabilisation is a prime requirement of any armoured fighting tank vehicle for military surveillance and weapon firing. Typically, such sighting systems have three prime electro-optical sensors i.e. day camera for viewing in day conditions, thermal camera for night viewing and eye-safe laser range finder for obtaining the target range. For laser guided missile firing, additional laser target designator may be a part of sighting system. This sighting system provides necessary parameters for the fire control computer to compute ballistic offsets to fire conventional ammunition or fire missile. System demands simultaneous interactions with electro-optical sensors, servo sensors, actuators, multi-function display for man-machine interface, fire control computer, logic controller and other sub-systems of tank. Therefore, a complex embedded electronics hardware is needed to respond in real time for such system. An efficient electronics embedded hardware architecture is presented here for the development of this type of sighting system. This hardware has been developed around SHARC 21369 processor and FPGA. A performance evaluation scheme is also presented for this sighting system based on the developed hardware.

Search and tracking in dynamic condition, rapid re-targeting, precision pointing and long range engagement in day and night condition are core requisite of stabilised sighting systems used for combat vehicles. Complex battle field requires integrated fire control system with stabilised sighting system as its main constituent. It facilitates quick reaction to fire control system and provides vital edge in the battlefield scenario. Precision gimbal design, optics design, embedded engineering, control system, electro-optical sensors, target detection and tracking, panorama generation, auto-alerting, digital image stabilisation, image fusion and integration are important aspects of sighting system development. In this paper, design considerations for a state of art stabilised sighting system have been presented including laboratory and field evaluation methods for such systems.