LiDAR plays an important role in the field of unmanned driving. Ground filtering is the key technology to separate and extract the ground information from the point cloud data acquired by LiDAR. Firstly, the development and classification of vehicle LiDAR scans (VLS) are introduced, and the advantages and disadvantages of all kinds of VLS are discussed. Then, the development of VLS ground filtering algorithm is studied and classified. The evaluation methods and standards of ground filtering accuracy are described, and three typical algorithms are compared and analyzed. Finally, the shortcomings of current VLS and its ground filtering algorithms are summarized, and the future development trend is prospected.

n cross-camera scenarios, it relies on the learning of label mapping relationships to improve recognition accuracy. The supervised person re-identification model has better recognition accuracy, but there are scalability problems. For example, the accuracy of algorithm identification relies heavily on effective supervised information. When adding a small amount of data in the classification process, all data needs to be reprocessed, resulting in poor real-time performance. Aiming at the above problems, an unsupervised person re-identification algorithm based on soft label is proposed. In order to improve the accuracy of label matching, first, learn soft multilabel to make it close to the real label, and obtain the reference agent by calculating the loss function of the reference data set to achieve the purpose of pre-training the reference data set. Then, calculate the expected value of the minimum distance between the generated data and the real data distribution (using the simplified 2-Wasserstein distance), calculate the mean and standard deviation vector of the soft multilabel in the camera view, and the resulting loss function can solve cross-view domain label consistency issues. In order to improve the validity of the soft tag on the unmarked target data set, the joint embedding loss is calculated, the similar pairs between different categories are mined, and the cross-domain distribution misalignment is corrected. In view of the problem that the residual network training duration and the unsupervised learning accuracy are low, the structure of the residual network is improved by combining the SENet and fusing multi-level depth feature to improve the training speed and accuracy. The experimental results show that the rank-1 and mAP are better than advanced correlation algorithms.

Existing works in person re-identification only considers extracting invariant feature representations from cross-view visible cameras, which ignores the imaging feature in infrared domain, such that there are few studies on visible-infrared relevant modality. Besides, most works distinguish two-views by often computing the similarity in feature maps from one single convolutional layer, which causes a weak performance of learning features. To handle the above problems, we design a feature pyramid random fusion network (FPRnet) that learns discriminative multiple semantic features by computing the similarities between multi-level convolutions when matching the person. FPRnet not only reduces the negative effect of bias in intra-modality, but also balances the heterogeneity gap between inter-modality, which focuses on an infrared image with very different visual properties. Meanwhile, our work integrates the advantages of learning local and global feature, which effectively solves the problems of visible-infrared person re-identification. Extensive experiments on the public SYSU-MM01 dataset from aspects of mAP and convergence speed, demonstrate the superiorities in our approach to the state-of-the-art methods. Furthermore, FPRnet also achieves competitive results with 32.12% mAP recognition rate and much faster convergence.

In order to solve the problems of sensitive initial contours and inaccurate segmentation caused by active contour segmentation of CT images, this paper proposes an automatic 3D vertebral CT active contour segmentation method combined weighted random forest called “WRF-AC”. This method proposes a weighted random forest algorithm and an active contour energy function that includes edge energy. First, the weighted random forest is trained by extracting 3D Haar-like feature values of the vertebra CT, and the 'vertebra center' obtained is used as the initial contour of the segmentation. Then, the segmentation of the vertebra CT image is completed by solving the active contour energy function minimum containing the edge energy. The experimental results show that this method can segment the spine CT images more accurately and quickly on the same datasets to extract the vertebrae.

In the image-based tip-tilt mirror control system, the closed-loop performance and bandwidth of the system and are limited due to the influence of sensor sampling frequency and system delay. Under the condition of limited bandwidth, this paper proposes to use linear encoder to measure the position, and get the rate signal by difference. The position-rate feedback control based on the image sensor system is realized to improve the error suppression ability of the tip-tilt mirror control system. Because of the addition of rate feedback, the control system has differential characteristics. When the rate feedback closed-loop is completed, the image position loop has integral characteristic. At this time, a PI controller is used to stabilize the system, which makes the system rise from zero type to two type system, and improves the error suppression ability of the system. Simulation and experiment show that this method can effectively improve the closed-loop performance of the tracking control system in low frequency domain.

As a new generation of the imaging device, light-field camera can simultaneously capture the spatial position and incident angle of light rays. However, the recorded light-field has a trade-off between spatial resolution and angular resolution. Especially the application range of light-field cameras is restricted by the limited spatial resolution of sub-aperture images. Therefore, a light-field super-resolution neural network that fuses multi-scale features to obtain super-resolved light-field is proposed in this paper. The deep-learning-based network framework contains three major modules: multi-scale feature extraction, global feature fusion, and up-sampling. Firstly, inherent structural features in the 4D light-field are learned through the multi-scale feature extraction module, and then the fusion module is exploited for feature fusion and enhancement. Finally, the up-sampling module is used to achieve light-field super-resolution. The experimental results on the synthetic light-field dataset and real-world light-field dataset showed that this method outperforms other state-of-the-art methods in both visual and numerical evaluations. In addition, the super-resolved light-field images were applied to depth estimation in this paper, the results illustrated that the disparity map was enhanced through the light-field spatial super-resolution.

Crack detection is one of the most important works in the system of pavement management. Cracks do not have a certain shape and the appearance of cracks usually changes drastically in different lighting conditions, making it hard to be detected by the algorithm with imagery analytics. To address these issues, we propose an effective U-shaped fully convolutional neural network called UCrackNet. First, a dropout layer is added into the skip connection to achieve better generalization. Second, pooling indices is used to reduce the shift and distortion during the up-sampling process. Third, four atrous convolutions with different dilation rates are densely connected in the bridge block, so that the receptive field of the network could cover each pixel of the whole image. In addition, multi-level fusion is introduced in the output stage to achieve better performance. Evaluations on the two public CrackTree206 and AIMCrack datasets demonstrate that the proposed method achieves high accuracy results and good generalization ability.

Aiming at the problem of water mist condensation on the fiber end face in a high-power fiber laser system, the most important factor causing this problem is that the traditional optical fiber connector does not have the moisture-proof sealing performance. The connector structure assembly and use process are analyzed in-depth, and the causes of the moisture-proof seal defects are pointed out. Through technological innovation and process improvement, a moisture-proof seal fiber connector is designed and completed. The principle and structure of the moisture-proof seal of the new connector are introduced. The main performances of the new connector are tested comprehensively, including immersion test, constant damp heat test, online application test. The experimental results show that the new connector has a better moisture-proof seal with IL less than 0.2 dB.

Aiming at the shortcoming of low serial operational efficiency in the quality-map-guided phase-unwrapping algorithm proposed by Miguel, an improved algorithm for parallel merging of multiple low-reliability blocks is proposed. Under the condition that the original algorithm design idea is satisfied, the unwrapping path is redefined as the largest reliable edge of the block. In addition, based on the non-continuous characteristic of the unwrapping path of the original algorithm, a low-reliability block out-of-order merging strategy is proposed to make multiple merging tasks can be performed simultaneously. The improved algorithm uses a multi-threaded software architecture. The main thread is responsible for looping through the unprocessed blocks to check whether they meet the requirements of merging, and the child threads receive and perform the merge tasks. The experimental results show that the improved method is completely consistent with the processing results of the original algorithm, and the parallel improvement strategy can effectively use the computer's multi-core resources, so that the operational efficiency of the phase unwrapping algorithm is improved by more than 50%.