High-speed Scene Research Articles

Multitarget-Tracking Method Based on the Fusion of Millimeter-Wave Radar and LiDAR Sensor Information for Autonomous Vehicles.

Multitarget tracking based on multisensor fusion perception is one of the key technologies to realize the intelligent driving of automobiles and has become a research hotspot in the field of intelligent driving. However, most current autonomous-vehicle target-tracking methods based on the fusion of millimeter-wave radar and lidar information struggle to guarantee accuracy and reliability in the measured data, and cannot effectively solve the multitarget-tracking problem in complex scenes. In view of this, based on the distributed multisensor multitarget tracking (DMMT) system, this paper proposes a multitarget-tracking method for autonomous vehicles that comprehensively considers key technologies such as target tracking, sensor registration, track association, and data fusion based on millimeter-wave radar and lidar. First, a single-sensor multitarget-tracking method suitable for millimeter-wave radar and lidar is proposed to form the respective target tracks; second, the Kalman filter temporal registration method and the residual bias estimation spatial registration method are used to realize the temporal and spatial registration of millimeter-wave radar and lidar data; third, use the sequential m-best method based on the new target density to find the track the correlation of different sensors; and finally, the IF heterogeneous sensor fusion algorithm is used to optimally combine the track information provided by millimeter-wave radar and lidar, and finally form a stable and high-precision global track. In order to verify the proposed method, a multitarget-tracking simulation verification in a high-speed scene is carried out. The results show that the multitarget-tracking method proposed in this paper can realize the track tracking of multiple target vehicles in high-speed driving scenarios. Compared with a single-radar tracker, the position, velocity, size, and direction estimation errors of the track fusion tracker are reduced by 85.5%, 64.6%, 75.3%, and 9.5% respectively, and the average value of GOSPA indicators is reduced by 19.8%; more accurate target state information can be obtained than a single-radar tracker.

Key frames assisted hybrid encoding for high-quality compressive video sensing.

Snapshot compressive imaging (SCI) encodes high-speed scene video into a snapshot measurement and then computationally makes reconstructions, allowing for efficient high-dimensional data acquisition. Numerous algorithms, ranging from regularization-based optimization and deep learning, are being investigated to improve reconstruction quality, but they are still limited by the ill-posed and information-deficient nature of the standard SCI paradigm. To overcome these drawbacks, we propose a new key frames assisted hybrid encoding paradigm for compressive video sensing, termed KH-CVS, that alternatively captures short-exposure key frames without coding and long-exposure encoded compressive frames to jointly reconstruct high-quality video. With the use of optical flow and spatial warping, a deep convolutional neural network framework is constructed to integrate the benefits of these two types of frames. Extensive experiments on both simulations and real data from the prototype we developed verify the superiority of the proposed method.

High-speed Scene Text Detection with Attention and Multi-scale Label Generation

High-speed Scene Text Detection with Attention and Multi-scale Label Generation

An Improved Convolutional Neural Network-Based Scene Image Recognition Method.

To solve the problems existing in the research of scene recognition, this paper studies a new convolutional neural network target detection model to achieve a better balance between the accuracy and speed of high-speed scene image recognition. First, aiming at the problem that the image is easy to be disturbed by impurities and poor quality in fine-grained image recognition, a preprocessing method based on the Canny edge detection is designed and the Canny operator is introduced to process the gray image. Second, the L2 regularization algorithm is used to optimize the basic network framework of the convolutional neural network, enhance the stability of the model in a complex environment, improve the generalization ability of the model, and improve the recognition accuracy of the algorithm to a certain extent. Finally, by collecting the campus environment datasets under different environmental conditions, the location recognition experiment and heat map visualization experiment are carried out. Experiments show that compared with the basic convolution neural network algorithm, the algorithm has better recognition performance and good generalization ability. The research of this study realizes the effective combination of multiframe convolution neural network and batch normalization algorithm and has a good practical effect on scene image recognition.

A novel offloading strategy for high speed mobile and data intensive intelligent sensor

In the paper, it proposes a novel offloading computing strategy for the mobile intelligent sensors in the high speed mobile scene. At present, the local computing resources are not able to afford the computing demand for the data intensive intelligent sensors. The current offloading computing mechanism are not capable of offloading computing in high speed scene. In general, it may cause extremely serious delay by the handover delay and the wireless channel fading. In the paper, the proposed novel strategy is named asynchronous parallel offloading computing strategy (APOCS). It makes use of one type of spatial computing diversity method to restrain the wireless channel fading. The simulation results show that it is able to reduce the offloading delay in the high speed moving scene effectively.

High-Speed Scene Flow on Embedded Commercial Off-the-Shelf Systems

Scene flow is an essential part of a stereo-based perception system for autonomous driving and mobile robotics. As in most of these platforms, the computing resource is limited but the computing requirement is high, embedded and parallelized algorithms are of vital importance for real-time tasks. This paper develops a cross-platform embedded scene flow algorithm by using an OpenCL (Open Computing Language) programming. Meanwhile, we propose a method to achieve a good performance by using a novel coarse-grained software pipeline for the embedded stream application. Experimental results show that the proposed algorithm can boost the average processing speed to 50 fps for different commercial off-the-shelf (COTS) hardware, including desktop graphics processing units (GPUs), field-programmable gate arrays (FPGAs), and mobile phone platforms. For certain GPUs, the peak frame rates can also reach 1000 fps. By comparing the efficiency among the serial platform, we illustrate that with the help of OpenCL programming, COTS platforms can provide enough computing resources for the stereo-based perception algorithm.

Compressive high-speed stereo imaging.

A compressive high-speed stereo imaging system is reported. The system is capable of reconstructing 3D videos at a frame rate 10 times higher than the sampling rate of the imaging sensors. An asymmetric configuration of stereo imaging system has been implemented by including a high-speed spatial modulator in one of the binocular views, and leaving the other view unchanged. We have developed a two-step reconstruction algorithm to recover the irradiance and depth information of the high-speed scene. The experimental results have demonstrated high-speed video reconstruction at 800fps from 80fps measurements. The reported compressive stereo imaging method does not require active illumination, offering a robust yet inexpensive solution to high-speed 3D imaging.

Spectral-temporal compressive imaging.

This Letter presents a compressive camera that integrates mechanical translation and spectral dispersion to compress a multi-spectral, high-speed scene onto a monochrome, video-rate detector. Experimental reconstructions of 17 spectral channels and 11 temporal channels from a single measurement are reported for a megapixel-scale monochrome camera.