Point cloud completion recovers the complete point clouds from partial ones, providing numerous point cloud information for downstream tasks such as 3-D reconstruction and target detection. However, previous methods usually suffer from unstructured prediction of points in local regions and the discrete nature of the point cloud. To resolve these problems, we propose a point cloud completion network called TPDC. Representing the point cloud as a set of unordered features of points with local geometric information, we devise a Triangular Pyramid Extractor (TPE), using the simplest 3-D structure-a triangular pyramid-to convert the point cloud to a sequence of local geometric information. Our insight of revealing local geometric information in a complex environment is to design a Divide-and-Conquer Splitting Module in a Divide-and-Conquer Splitting Decoder (DCSD) to learn point-splitting patterns that can fit local regions the best. This module employs the Divide-and-Conquer approach to parallelly handle tasks related to fitting ground-truth values to base points and predicting the displacement of split points. This approach aims to make the base points align more closely with the ground-truth values while also forecasting the displacement of split points relative to the base points. Furthermore, we propose a more realistic and challenging benchmark, ShapeNetMask, with more random point cloud input, more complex random item occlusion, and more realistic random environmental perturbations. The results show that our method outperforms both widely used benchmarks as well as the new benchmark.

It is difficult to recognise an image with affine transformation due to viewing angle anddistance variations. Therefore, affine invariant feature extraction is avaluable technology in the field of image recognition. Inspired by bio‐visualmechanism, an affine invariant for object recognition method based on a fusionfeature framework is proposed in this study, which employs geometry descriptorand double biologically inspired transformation (DBIT). First, a shape featureof interest detector is adopted to detect contour features. Then, the areaestimation of affine region detector is utilised to construct area ratio featurevectors. Second, an orientation edge detector is built to highlight the edges ofdifferent directions. On this basis, local space frequency detector is adoptedto measure the spatial frequency at each direction and interval, which convertsthe output map into DBIT feature vectors. A weighted fusion strategy isperformed based on Pearson correlation distance to fuse the geometry feature andDBIT feature. Some tests for Alphanumeric, Coil‐100 MPEG‐7, Mixed NationalInstitute of Standards and Technology (MNIST) and Olivetti Research Laboratoryface images database (ORL) database remain highly stable recognition accuracy,even when the shear factor is between −0.5 and + 0.5. The experiment resultsshow the authors’ proposed approach has a nice performance in featureinvariance, selectivity and recognition accuracy.

It is significant to extract rotation, scaling, translation, and noise (RSTN) invariant features inspired by biological vision for image recognition. A bionic RSTN‐invariant feature extraction are proposed. This extraction process comprises two stages. In the first stage, a novel orientation edge detection is designed based on a filter‐to‐filter scheme. Gabor filters, a bottom filter, smoothen an image by simulating biological vision. Bipolar filters, a top filter, detect the horizontal and vertical direction orientation edge by simulating vision cortex response. After obtaining the orientation edge of the image, an interval detector is executed by a spatial frequency of different direction and distance. Then, the interval detection results are transformed into pixels of the orientation‐interval feature map. RSTN invariant features are generated through the repetition of orientation edge detection and interval detection. Several experimental results demonstrate that RSTN‐invariant features have striking robustness, and capable to classify RSTN images. Finally, bionic invariant features are practiced in traffic sign recognition.

For dynamic path planning problem under unstructured environment, firstly, successive edge following and least squares method (SEF-LSM) is adopted to extract environment characteristics of laser rangefinder data, and SEF-LSM with logical reasoning (SEF-LSM-LR) is proposed for dynamic obstacles characteristics detection. Furthermore, the perpendicularity (PERP) algorithm is utilized to identify dynamic vehicle, according to the perpendicularity attribute of vehicle. Secondly, all the laser rangefinder scanning points are marked as negative ([Formula: see text]) or positive ([Formula: see text]1), and the scanning points of one dynamic obstacle are marked as the same label. Thirdly, extended support vector machine (ESVM) is designed for outdoor robot local path planning under unstructured environment, which consider the practical start-goal position and heading constraints, robot kinematic constraint, and curvature constraint, moreover, the emergency obstacle is regarded as disturbances during planning processing. Finally, the optimal path is chosen by the shortest distance evaluation function. Lots of outdoor simulations show that the proposed method solve the dynamic planning problem under unstructured environment, and their effectiveness performance are verified for outdoor robot path planning.