Huazhong University of Science and Technology

Yimeng Chen

Tianxu Zhang

Sufei Fan

Zheng Wang

Heng Yao

Li Liu

Wei Huang

Longwei Hao

Wenxuan Ma

Xuan Hou

Chuan Zhang

Zhihui Yang

Zhenghua Huang

Yayun Zheng

Zhengtao Li

Xudong He

Changsheng Chen

Huan Wu

Peng Jiang

Li He

The present invention provides an above-ground building recognition method, including the following steps: (1) taking an infrared image of the ground from the air; (2) performing detection and positioning in the infrared image to determine a suspected target; (3) aiming at the suspected target to perform laser imaging; (4) performing range gating on a laser image to filter out foreground and background interference; and (5) extracting a shape feature of the suspected target from the laser image with interference filtered out, and taking the shape feature as a target matching element to perform matching with a target shape feature template, so as to recognize the target. In the method of the present invention, laser imaging is integrated into infrared imaging target positioning, so that an advantage of a large range of infrared imaging is utilized, and three-dimensional range information of laser imaging is also utilized, thereby effectively improving the precision of positioning a building.

Above-ground building recognition method and navigation method combining laser and infrared

A de-noising method for remote images of ground buildings using spectrum constraints. The method includes: 1) obtaining a reference image of ground buildings from a remote image database of the ground buildings, performing a Fourier transformation on the reference image to obtain an amplitude spectrum, and performing a threshold segmentation, an erosion operation and a dilation operation successively on the amplitude spectrum to obtain a binary template of spectrum of the ground buildings; and 2) obtaining a real-time image of the ground buildings by a high-speed aircraft, performing a Fourier transformation on the real-time image to obtain a spectrum, filtering the spectrum of the real-time image in frequency domain by the binary template of spectrum of the ground buildings, and performing an inverse Fourier transformation thereon to generate a filtered real-time image of the ground buildings.

De-noising system for remote images of ground buildings using spectrum constraints and de-noising method thereof

The present invention discloses a multi-sensor merging based super-close distance autonomous navigation apparatus and method. The apparatus includes a sensor subsystem, an information merging subsystem, a sensor scanning structure, and an orientation guiding structure, wherein a visible light imaging sensor and an infrared imaging sensor are combined together, and data are acquired by combining a passive measurement mode composed of an optical imaging sensor and an active measurement mode composed of a laser distance measuring sensor. Autonomous navigation is divided into three stages, that is, a remote distance stage, implemented by adopting a navigation mode where a binocular visible light imaging sensor and a binocular infrared imaging sensor are combined, a close distance stage, implemented by adopting a navigation mode where a binocular visible light imaging sensor, a binocular infrared imaging sensor and a laser distance measuring sensor array are combined, and an ultra-close distance stage, implemented by adopting a navigation mode of a laser distance measuring sensor array. Through the present invention, the field of view and the exploration range are widened, the problem of shielding existing in passive measurement is effectively solved, the precision of data measurement is ensured, and the navigation efficiency and the safety and reliability of navigation are improved.

Multi-sensor merging based super-close distance autonomous navigation apparatus and method

A method for estimating a rotation axis and a mass center of a spatial target based on binocular optical flows. The method includes: extracting feature points from binocular image sequences sequentially and respectively, and calculating binocular optical flows formed thereby; removing areas ineffective for reconstructing a three-dimensional movement trajectory from the binocular optical flows of the feature points, whereby obtaining effective area-constrained binocular optical flows, and reconstructing a three-dimensional movement trajectory of a spatial target; and removing areas with comparatively large errors in reconstructing three-dimensional motion vectors from the optical flows by multiple iterations, estimating a rotation axis according to a three-dimensional motion vector sequence of each of the feature points obtained thereby, obtaining a spatial equation of an estimated rotation axis by weighted average of estimated results of the feature points, and obtaining spatial coordinates of a mass center of the target according to two estimated rotation axes.

Method for estimating rotation axis and mass center of spatial target based on binocular optical flows

Growing community of inventors

Hubei, China

Yimeng Chen