Spatio-Temporal Context-Guided Algorithm for Lossless Point Cloud Geometry Compression

Point cloud compression is critical to deploy 3D representation of the physical world such as 3D immersive telepresence,autonomous driving,and cultural heritage preservation.However,point cloud data are distributed irregularly and discontinuously in spatial and temporal domains,where redundant unoccupied voxels and weak correlations in 3D space make achieving efficient compression a challenging problem.In this paper,we propose a spatio-temporal context-guided algorithm for lossless point cloud geometry compression.The proposed scheme starts with dividing the point cloud into sliced layers of unit thickness along the longest axis.Then,it introduces a prediction method where both intraframe and inter-frame point clouds are available,by determining correspondences between adjacent layers and estimating the shortest path using the travelling salesman algorithm.Finally,the few prediction residual is efficiently compressed with optimal context-guided and adaptive fastmode arithmetic coding techniques.Experiments prove that the proposed method can effectively achieve low bit rate lossless compression of point cloud geometric information,and is suitable for 3D point cloud compression applicable to various types of scenes.

DSP编程的关键问题

对DSP串口的DMA传输方式使用中可能遇到的疑难问题、汇编指令歧义及C语言混合编程容易犯的错误作了分析,对Bootload编程的疑难点做出了相应实例解释。

M-FCN based sea-surface weak target detection

This paper focuses on the sea-surface weak target detection based on memory-fully convolutional network(M-FCN)in strong sea clutter.Firstly,the constant false alarm rate(CFAR)detection method utilizes a low threshold with high probability of false alarm to detect sea-surface weak targets after non-coherent integration.Reducing the detection threshold can generate a large number of false alarms while increasing the detection rate,and how to suppress a large number of false alarms is the key to improve the performance of weak target detection.Then,the detection result of the low threshold is operated to construct the target matrix suitable for the size of fully convolutional networks and the convolution operator form.Finally,the M-FCN architecture is designed to learn the different accumulation characteristics of the target and the sea clutter between different frames.For improving the detection performance,the historical multi-frame information is memorized by the network,and the end-to-end structure is established to detect sea-surface weak target automatically.Experimental results on measured data demonstrate that the M-FCN method outperforms the traditional track before detection(TBD)method and reduces false alarm tracks by 35.1%,which greatly improves the track quality.

DSP编程中几个关键问题的探究

对DSP串口的DMA传输方式使用中可能遇到的疑难问题、汇编指令歧义及C语言混合编程容易犯的错误作了分析,对Bootload编程的疑难点做出了相应实例解释。

FaSRnet:a feature and semantics refinement network for human pose estimation

Due to factors such as motion blur,video out-of-focus,and occlusion,multi-frame human pose estimation is a challenging task.Exploiting temporal consistency between consecutive frames is an efficient approach for addressing this issue.Currently,most methods explore temporal consistency through refinements of the final heatmaps.The heatmaps contain the semantics information of key points,and can improve the detection quality to a certain extent.However,they are generated by features,and feature-level refinements are rarely considered.In this paper,we propose a human pose estimation framework with refinements at the feature and semantics levels.We align auxiliary features with the features of the current frame to reduce the loss caused by different feature distributions.An attention mechanism is then used to fuse auxiliary features with current features.In terms of semantics,we use the difference information between adjacent heatmaps as auxiliary features to refine the current heatmaps.The method is validated on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018,and the results demonstrate the effectiveness of our method.

Abnormal event detection via the analysis of multi-frame optical flow information

Security surveillance of public scene is closely relevant to routine safety of individual.Under the stimulus of this concern,abnormal event detection is becoming one of the most important tasks in computer vision and video processing.In this paper,we propose a new algorithm to address the visual abnormal detection problem.Our algorithm decouples the problem into a feature descriptor extraction process,followed by an AutoEncoder based network called cascade deep AutoEncoder(CDA).The movement information is represented by a novel descriptor capturing the multi-frame optical flow information.And then,the feature descriptor of the normal samples is fed into the CDA network for training.Finally,the abnormal samples are distinguished by the reconstruction error of the CDA in the testing procedure.We validate the proposed method on several video surveillance datasets.

Multi-frame and multi-dimensional historical digital cities: the Como example

In this article,we present the realisation of a multi-frame and multi-dimensional WebGIS that allows users to simultaneously analyse a specific portion of the Earth taking into account the historical information,too.Two graphical panels have been realised:one for the usual 2D view and one for a more realistic 3D view.Both panels display historical maps of the city,the current orthophoto and the digital topographical map.The 3D frame is based on NASA World Wind,an open source virtual globe from where 3D buildings are shown extruding the 2D shapes using their mean height.Thanks to a specifically designed graphical user interface,it is also possible to dynamically thematise the buildings on the globe according to different criteria(e.g.the construction time span)so that only the geometries fulfilling the request are turned on.Within the proposed application,a synchronisation between the two panels has been implemented,in order to maintain a constant alignment of the two viewers.The application is also open to the time dimension.In fact,assigning to each geometry two dates(e.g.‘year of construction’and‘year of demolition’),it is possible to dynamically view how buildings have changed over time,both in their shape and height.Future developments of this work will concern the possibility of implementing a city model with a higher level of detail.

A multi-frame track-before-detect algorithm based on root label clustering for multiple targets

In this paper,a novel multi-frame track-before-detect algorithm is proposed,which is based on root label clustering to reduce the high computational complexity arising by observation area expansion and clutter/noise density increase.A criterion of track extrapolation is used to construct state transition set,root label is marked by state transition set to obtain the distribution information of multiple targets in measurement space,then measurement plots of multi-frame are divided into several clusters,and finally multi-frame track-before-detect algorithm is implemented in each cluster.The computational complexity can be reduced by employing the proposed algorithm.Simulation results show that the proposed algorithm can accurately detect multiple targets in close proximity and reduce the number of false tracks.