Tracking features in image sequences suffers from varying illumination and viewpoints. In
recent years, learning-based features have achieved higher repeatability in challenging …

In recent decades, with the ever-growing scale of video data, near-duplicate videos continue
to emerge. Data quality issues caused by near-duplicate videos are becoming more and …

Road obstacle detection is an important component of the advanced driver assistance
system, and to improve the speed and accuracy of road obstacle detection method is a vital …

针对现有的Harris 角点提取算法在图像匹配法中, 存在精度低, 抗干扰和抗光照变化能力弱的
缺陷, 提出一种基于局部二进制模式(Local Binary Patterns, LBP) 和图变换匹配算法(Graph …

Circular-harmonic spectra are a compact representation of local image features in two
dimensions. It is well known that the computational complexity of such transforms is greatly …

Random decision forests have been used extensively in a number of areas of computer
vision, such as scene classification, segmentation and object detection. In previous works of …

With the increasing demand for indoor positioning, VIO (visual inertial odometer) are
receiving more and more attention due to the universality and convenience of the camera …

Pattern detection is a well-studied area of computer vision, but still current methods are
unstable in images of poor quality. This thesis describes improvements over contemporary …