Huazhong University of Science and Technology

Nong Sang

Changxin Gao

Weidong Yang

Tianxu Zhang

Yuehuan Wang

Cen Lu

Longwei Hao

Wenxuan Ma

Yuanjie Shao

Shiwei Zhang

Luxin Yan

Lerenhan Li

Jin Wang

Juncai Peng

Heng Yao

Zhiyuan Li

Ruochen Zheng

Hu Zhu

Chuchu Han

Hao Yan

Zhixiong Pi

The invention discloses a person search method based on person re-identification driven localization refinement. On one hand, the region of interest (ROI) conversion module converts an original input image into a small image corresponding to a ROI, and contradiction existing in part of features shared by a person re-identification network and a detection network is avoided; and on the other hand, loss of the person re-identification network can be transmitted back to the detection network in a gradient manner through the ROI conversion module, the supervision of loss of the person re-identification network for the detection bounding box output by the detection network is realized, and the adjusted detection bounding box can effectively remove background interference, contains more useful attribute information and is more suitable for person search, so that the person search accuracy is greatly improved.

Person search method based on person re-identification driven localization refinement

A spatiotemporal action detection method includes performing object detection on all frames of a sample video to obtain a candidate object set; calculating all interframe optical flow information on the sample video to obtain a motion set; constructing a spatiotemporal convolution-deconvolution network of an attention mechanism and a motion attention mechanism of an additional object; adding both a corresponding sparse variable and a sparse constraint to obtain a network structure S after performing spatiotemporal convolution processing on each time segment of the sample video; training the network structure S with an objective function based on classification loss and loss of the sparse constraint of cross entropy; and calculating an action category and a sparse coefficient corresponding to each time segment of a test sampled video to obtain an object action spatiotemporal location.

Spatiotemporal action detection method

The present invention discloses a method and system for selecting an image region that facilitates blur kernel estimation, in which the method includes: calculating a relative total variation value of each pixel in a blurred image to obtain a relative total variation mapping image; setting a threshold value to determine whether respective pixel in the image is a boundary pixel or not; then sampling the blurred image and its relative total variation mapping image to obtain a series of image patches; and finally counting the number of boundary pixels in each mapping image patch and selecting out an image region that facilitates blur kernel estimation. According to the method and the system, the problems of excessive dependency on operator experience, low efficiency and the like in the existing region selection methods are effectively solved. The image region that facilitates blur kernel estimation is automatically selected out. And the method and the system are suitable for the application occasion of the blur kernel estimation in an image deblurring algorithm.

Method and system for selecting image region that facilitates blur kernel estimation

The present invention provides a method for infrared imaging detection and positioning of an underground tubular facility in a plane terrain. Demodulation processing is performed on an original infrared image formed after stratum modulation is generated on the underground tubular facility according to an energy diffusion Gaussian model of the underground tubular facility, so as to obtain a target image of the underground tubular facility. The method comprises: obtaining an original infrared image g formed after stratum modulation is generated on an underground tubular facility; setting an initial value hof a Gaussian thermal diffusion function according to the original infrared image g; using the original infrared image g as an initial target image f, and performing, according to the initial value hof the Gaussian thermal diffusion function, iteration solution of a thermal diffusion function hand a target image fby by using a single-frame image blind deconvolution method based on a Bayesian theory; and determining whether an iteration termination condition is met, and if the iteration termination condition is met, determining that the target image fobtained by means of iteration solution this time is a final target image f; and if the iteration termination condition is not met, continuing the iteration calculation. By means of the method, the display of the infrared image of the original underground tubular facility is clearer, and the real structure of the underground tubular facility can also be inverted.

Method for infrared imaging detection and positioning of underground tubular facility in plane terrain

A method for estimating a blur kernel size, the method including: (1) pre-processing a blurred image, to obtain an image, so that a size of the image satisfies an image input size of a multi-class convolutional neural network (CNN); (2) inputting the image into a multi-class CNN with completed training, to obtain a blur-kernel-size probability distribution vector; and (3) comparing each element in the blur-kernel-size probability distribution vector, so that an estimated blur kernel size of the blurred image is the blur kernel size corresponding to a largest element. The invention also provides a system for estimating a blur kernel size. The system includes an image pre-processing module, a training-set synthesizing module, a multi-class CNN module, and a blur kernel size estimation module.

Method and system for estimating blur kernel size

The invention discloses a method for correcting aero-optical thermal radiation noise, comprising steps of: pretreating a degraded image to obtain a multi-scale degraded image group, conducting iteration process of obtaining an optimal solution by using a last scale estimation result as an original value of next scale estimation according to the multi-scale degraded image group, thereby facilitating original-scale bias field estimation, and restoring the degraded image according to the original-scale bias field estimated value thereby obtaining an image after aero-optical thermal radiation noise correction. The invention also discloses a system for correcting aero-optical thermal radiation noise. The invention is capable of solving problems with conventional methods, comprising poor correction effect, high complexity, and incapability in correcting the thermal radiation noise at an image level, and applicable to restoration of an image with aero-optical thermal radiation noise.

Method and system for correcting aero-optical thermal radiation noise

An infrared imaging detection and positioning method for an underground building in a planar land surface environment comprises: obtaining an original infrared image gformed after stratum modulation is performed on an underground building, and determining a local infrared image g of a general position of the underground building in the original infrared image g; setting an iteration termination condition, and setting an initial value hof a Gaussian thermal diffusion function; using the local infrared image g as an initial target image f, and performing iteration solution of a thermal expansion function hand a target image fby using a maximum likelihood estimation algorithm according to the initial value hof the Gaussian thermal diffusion function; and determining whether the iteration termination condition is met, if the iteration termination condition is met, using the target image fobtained by means of iteration solution this time as a final target image f; and if the iteration termination condition is not met, continuing to perform iteration calculation. In the method, by performing demodulation processing on the infrared image formed after stratum modulation is performed on the underground building, the display of the infrared image of the original underground building is clearer, and the real structure of the underground building can be inverted.

Infrared imaging detection and positioning method for underground building in planar land surface environment

The present invention discloses a method for detecting, recognizing, and positioning a zonal underground target in a mountain land environment by detecting a ridge position in the mountain land environment and carrying out energy correction. The method belongs to the interdisciplinary field of pattern recognition, remote sensing technology and terrain analysis. The zonal underground target can cause energy abnormity when the heat field thereof is different from that of a mountain mass, and the heat island effect of the ridge can also cause the energy of the mountain mass to be abnormal. However, the energy abnormity caused by the heat island effect is essentially different from the energy abnormity caused by the zonal underground target in the aspect of mode. Therefore, the present invention aims to achieve an effect of reducing a false alarm rate of detecting and recognizing a zonal underground target in the mountain land environment by eliminating the influence of the heat body effect generated by the ridge in the terrain on the weak energy abnormity mode presented by the zonal underground target. The present invention comprises steps of acquiring digital elevation information of terrain, performing de-noising pretreatment on the digital elevation information, detecting a ridge line, correcting energy at the ridge position, and detecting the zonal underground target.

Method for detecting zonal underground target in mountain land based on ridge heat radiation correction

A zonal underground structure detection method based on sun shadow compensation is provided, which belongs to the crossing field of remote sensing technology, physical geography and pattern recognition, and is used to carry out compensation processing after a shadow is detected, to improve the identification rate of zonal underground structure detection and reduce the false alarm rate. The present invention comprises steps of acquiring DEM terrain data of a designated area, acquiring an image shadow position by using DEM, a solar altitude angle and a solar azimuth angle, processing and compensating a shadow area, and detecting a zonal underground structure after the shadow area is corrected. In the present invention, the acquired DEM terrain data is used to detect the shadow in the designated area; and the detected shadow area is processed and compensated, to reduce influence of the shadow area on zonal underground structure detection; finally, the zonal underground structure is detected by using a remote sensing image after shadow compensation, so that the accuracy of zonal underground structure detection is improved and the false alarm rate is reduced compared with zonal underground structure detection using a remote sensing image without shadow compensation processing.

Growing community of inventors

Hubei, China

Nong Sang