scholarly journals Vehicle Motion State Prediction Method Integrating Point Cloud Time Series Multiview Features and Multitarget Interactive Information

2022 ◽  
Vol 2022 ◽  
pp. 1-21
Author(s):  
Ruibin Zhang ◽  
Yingshi Guo ◽  
Yunze Long ◽  
Yang Zhou ◽  
Chunyan Jiang
Keyword(s):  
Point Cloud ◽  
Short Term Memory ◽  
Time Sequence ◽  
Object Motion ◽  
Intelligent Vehicles ◽  
Prediction Algorithm ◽  
Interaction Information ◽  
Motion State ◽  
State Prediction ◽  
Vehicle Motion

A vehicle motion state prediction algorithm integrating point cloud timing multiview features and multitarget interaction information is proposed in this work to effectively predict the motion states of traffic participants around intelligent vehicles in complex scenes. The algorithm analyzes the characteristics of object motion that are affected by the surrounding environment and the interaction of nearby objects and is based on the complex traffic environment perception dual multiline light detection and ranging (LiDAR) technology. The time sequence aerial view map and time sequence front view depth map are obtained using real-time point cloud information perceived by the LiDAR. Time sequence high-level abstract combination features in the multiview scene are then extracted by an improved VGG19 network model and are fused with the potential spatiotemporal interaction of the multitarget operation state data extraction features detected by the laser radar by using a one-dimensional convolution neural network. A temporal feature vector is constructed as the input data of the bidirectional long-term and short-term memory (BiLSTM) network, and the desired input-output mapping relationship is trained to predict the motion state of traffic participants. According to the test results, the proposed BiLSTM model based on point cloud multiview and vehicle interaction information is better than other methods in predicting the state of target vehicles. The results can provide support for the research to evaluate the risk of intelligent vehicle operation environment.

scholarly journals A graph-based CNN-LSTM stock price prediction algorithm with leading indicators

2021 ◽  
Author(s):  
Jimmy Ming-Tai Wu ◽  
Zhongcui Li ◽  
Norbert Herencsar ◽  
Bay Vo ◽  
Jerry Chun-Wei Lin
Keyword(s):  
Neural Network ◽  
Stock Market ◽  
Financial Management ◽  
Stock Price ◽  
Short Term Memory ◽  
Prediction Algorithm ◽  
Leading Indicators ◽  
Stock Price Prediction ◽  
Price Prediction ◽  
Wealth Management

AbstractIn today’s society, investment wealth management has become a mainstream of the contemporary era. Investment wealth management refers to the use of funds by investors to arrange funds reasonably, for example, savings, bank financial products, bonds, stocks, commodity spots, real estate, gold, art, and many others. Wealth management tools manage and assign families, individuals, enterprises, and institutions to achieve the purpose of increasing and maintaining value to accelerate asset growth. Among them, in investment and financial management, people’s favorite product of investment often stocks, because the stock market has great advantages and charm, especially compared with other investment methods. More and more scholars have developed methods of prediction from multiple angles for the stock market. According to the feature of financial time series and the task of price prediction, this article proposes a new framework structure to achieve a more accurate prediction of the stock price, which combines Convolution Neural Network (CNN) and Long–Short-Term Memory Neural Network (LSTM). This new method is aptly named stock sequence array convolutional LSTM (SACLSTM). It constructs a sequence array of historical data and its leading indicators (options and futures), and uses the array as the input image of the CNN framework, and extracts certain feature vectors through the convolutional layer and the layer of pooling, and as the input vector of LSTM, and takes ten stocks in U.S.A and Taiwan as the experimental data. Compared with previous methods, the prediction performance of the proposed algorithm in this article leads to better results when compared directly.

scholarly journals Pyramid Constrained Self-Attention Network for Fast Video Salient Object Detection

2020 ◽  
Vol 34 (07) ◽  
pp. 10869-10876 ◽  
Author(s):  
Yuchao Gu ◽  
Lijuan Wang ◽  
Ziqin Wang ◽  
Yun Liu ◽  
Ming-Ming Cheng ◽  
...  
Keyword(s):  
Object Detection ◽  
Short Term Memory ◽  
Salient Object Detection ◽  
Object Motion ◽  
Salient Object ◽  
Motion Cues ◽  
Spatiotemporal Information ◽  
Local Mechanism ◽  
Non Local ◽  
Pyramid Structures

Spatiotemporal information is essential for video salient object detection (VSOD) due to the highly attractive object motion for human's attention. Previous VSOD methods usually use Long Short-Term Memory (LSTM) or 3D ConvNet (C3D), which can only encode motion information through step-by-step propagation in the temporal domain. Recently, the non-local mechanism is proposed to capture long-range dependencies directly. However, it is not straightforward to apply the non-local mechanism into VSOD, because i) it fails to capture motion cues and tends to learn motion-independent global contexts; ii) its computation and memory costs are prohibitive for video dense prediction tasks such as VSOD. To address the above problems, we design a Constrained Self-Attention (CSA) operation to capture motion cues, based on the prior that objects always move in a continuous trajectory. We group a set of CSA operations in Pyramid structures (PCSA) to capture objects at various scales and speeds. Extensive experimental results demonstrate that our method outperforms previous state-of-the-art methods in both accuracy and speed (110 FPS on a single Titan Xp) on five challenge datasets. Our code is available at https://github.com/guyuchao/PyramidCSA.

scholarly journals A Hierarchical Deep Fusion Framework for Egocentric Activity Recognition Using a Wearable Hybrid Sensor System

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 546 ◽  
Author(s):  
Haibin Yu ◽  
Guoxiong Pan ◽  
Mian Pan ◽  
Chong Li ◽  
Wenyan Jia ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Short Term Memory ◽  
Specific Activity ◽  
Negative Influence ◽  
Sensor System ◽  
Sensor Data ◽  
Motion Sensor ◽  
Motion Sensors ◽  
Motion State ◽  
Fusion Framework

Recently, egocentric activity recognition has attracted considerable attention in the pattern recognition and artificial intelligence communities because of its wide applicability in medical care, smart homes, and security monitoring. In this study, we developed and implemented a deep-learning-based hierarchical fusion framework for the recognition of egocentric activities of daily living (ADLs) in a wearable hybrid sensor system comprising motion sensors and cameras. Long short-term memory (LSTM) and a convolutional neural network are used to perform egocentric ADL recognition based on motion sensor data and photo streaming in different layers, respectively. The motion sensor data are used solely for activity classification according to motion state, while the photo stream is used for further specific activity recognition in the motion state groups. Thus, both motion sensor data and photo stream work in their most suitable classification mode to significantly reduce the negative influence of sensor differences on the fusion results. Experimental results show that the proposed method not only is more accurate than the existing direct fusion method (by up to 6%) but also avoids the time-consuming computation of optical flow in the existing method, which makes the proposed algorithm less complex and more suitable for practical application.

scholarly journals Continuous Gesture Recognition Based on Time Sequence Fusion Using MIMO Radar Sensor and Deep Learning

Electronics ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 869 ◽  
Author(s):  
Wentai Lei ◽  
Xinyue Jiang ◽  
Long Xu ◽  
Jiabin Luo ◽  
Mengdi Xu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Gesture Recognition ◽  
Continuous Wave ◽  
Short Term Memory ◽  
Estimation Algorithm ◽  
Intermediate Frequency ◽  
Mimo Radar ◽  
Time Sequence ◽  
Band Pass Filter ◽  
Pass Filter

Gesture recognition that is based on high-resolution radar has progressively developed in human-computer interaction field. In a radar recognition-based system, it is challenging to recognize various gesture types because of the lacking of gesture transversal feature. In this paper, we propose an integrated gesture recognition system that is based on frequency modulated continuous wave MIMO radar combined with deep learning network for gesture recognition. First, a pre-processing algorithm, which consists of the windowed fast Fourier transform and the intermediate-frequency signal band-pass-filter (IF-BPF), is applied to obtain improved Range Doppler Map. A range FFT based MUSIC (RFBM) two-dimensional (2D) joint super-resolution estimation algorithm is proposed to obtain a Range Azimuth Map to obtain gesture transversal feature. Range Doppler Map and Range Azimuth Map then respectively form a Range Doppler Map Time Sequence (RDMTS) and a Range Azimuth Map Time Sequence (RAMTS) in gesture recording duration. Finally, a Dual stream three-dimensional (3D) Convolution Neural Network combined with Long Short Term Memory (DS-3DCNN-LSTM) network is designed to extract and fuse features from both RDMTS and RAMTS, and then classify gestures with radial and transversal change. The experimental results show that the proposed system could distinguish 10 types of gestures containing transversal and radial motions with an average accuracy of 97.66%.

scholarly journals TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents

2019 ◽  
Vol 33 ◽  
pp. 6120-6127 ◽  
Author(s):  
Yuexin Ma ◽  
Xinge Zhu ◽  
Sibo Zhang ◽  
Ruigang Yang ◽  
Wenping Wang ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Short Term Memory ◽  
Autonomous Vehicle ◽  
Large City ◽  
Urban Traffic ◽  
Heterogeneous Traffic ◽  
Prediction Algorithm ◽  
Trajectory Prediction ◽  
Long Short Term Memory ◽  
Traffic Agents

To safely and efficiently navigate in complex urban traffic, autonomous vehicles must make responsible predictions in relation to surrounding traffic-agents (vehicles, bicycles, pedestrians, etc.). A challenging and critical task is to explore the movement patterns of different traffic-agents and predict their future trajectories accurately to help the autonomous vehicle make reasonable navigation decision. To solve this problem, we propose a long short-term memory-based (LSTM-based) realtime traffic prediction algorithm, TrafficPredict. Our approach uses an instance layer to learn instances’ movements and interactions and has a category layer to learn the similarities of instances belonging to the same type to refine the prediction. In order to evaluate its performance, we collected trajectory datasets in a large city consisting of varying conditions and traffic densities. The dataset includes many challenging scenarios where vehicles, bicycles, and pedestrians move among one another. We evaluate the performance of TrafficPredict on our new dataset and highlight its higher accuracy for trajectory prediction by comparing with prior prediction methods.

scholarly journals SEMANTIC SEGMENTATION OF MOBILE LASER SCANNING POINT CLOUDS WITH LONG SHORT-TERM MEMORY NETWORKS: PRELIMINARY RESULTS

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 123-130
Author(s):  
J. Balado ◽  
P. van Oosterom ◽  
L. Díaz-Vilariño ◽  
P. Arias
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Short Term Memory ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Time Signal ◽  
Success Rates ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Abstract. Although point clouds are characterized as a type of unstructured data, timestamp attribute can structure point clouds into scanlines and shape them into a time signal. The present work studies the transformation of the street point cloud into a time signal based on the Z component for the semantic segmentation using Long Short-Term Memory (LSTM) networks. The experiment was conducted on the point cloud of a real case study. Several training sessions were performed changing the Level of Detail of the classification (coarse level with 3 classes and fine level with 11 classes), two levels of network depth and the use of weighting for the improvement of classes with low number of points. The results showed high accuracy, reaching at best 97.3% in the classification with 3 classes (ground, buildings, and objects) and 95.7% with 11 classes. The distribution of the success rates was not the same for all classes. The classes with the highest number of points obtained better results than the others. The application of weighting improved the classes with few points at the expense of the classes with more points. Increasing the number of hidden layers was shown as a preferable alternative to weighting. Given the high success rates and a behaviour of the LSTM consistent with other Neural Networks in point cloud processing, it is concluded that the LSTM is a feasible alternative for the semantic segmentation of point clouds transformed into time signals.

Sign in / Sign up

Export Citation Format

Share Document