Search

A wide dynamic range CMOS image sensor is proposed, exhibiting a linear response at a low illumination level and a logarithmic response at a high illumination level. To maintain high sensitivity and to improve the dynamic range of the proposed pixel, a cascode MOSFET is integrated into the structure of the proposed pixel, along with a photogate. The applied photogate voltage reduces the sensitivity of the proposed pixel under the linear response regime, at a moderate illumination level. Under high illumination levels, the biased cascode MOSFET serves as a voltage-light-dependent active load and is responsible for logarithmic operation. The dynamic range of the proposed pixel can be improved by adjusting the sensitivity and the basis of the logarithmic response.

Voxelisation methods are extensively employed for efficiently processing large point clouds. However, it is possible to lose geometric information and extract inaccurate features through these voxelisation methods. A novel, flexibly shaped ‘supervoxel’ algorithm, called boundary-enhanced supervoxel segmentation, for sparse and complex outdoor light detection and ranging (LiDAR) data is proposed. The algorithm consists of two key components: (i) detecting boundaries by analysing consecutive points and (ii) clustering the points by first excluding the boundary points. The generated supervoxels include spatial and geometric properties and maintain the shape of the object's boundary. The proposed algorithm is tested using sparse LiDAR data obtained from outdoor urban environments.

A new method for detecting drivable regions in an unrehearsed and unstructured outdoor environment using multi-sensor information is presented. To achieve this goal, two key methods are developed: (i) robust and effective feature definition using colour and geometry and (ii) online learning algorithm using positive samples for detecting drivable regions. With real data sets, the effect of sensor modality is evaluated and is compared the performance of the algorithm to a cluster-based approach.

Presented is a wheelchair control using a head pose free eye-gaze estimation. The direction of the wheelchair is computed from a user's eye-gaze pointing. The eye-gaze estimation system includes a 3D orientation sensor to take into account the head pose. Therefore, the user can change his or her pose with comfort during navigation. In experiments, its performance was evaluated in comparison with a manual keyboard control.