Construction of Subjective Vehicle Detection Evaluation Model Considering Shift from Ground Truth Position

2019 ◽  
Vol E102.A (9) ◽  
pp. 1246-1249 ◽  
Author(s):  
Naho ITO ◽  
Most Shelina AKTAR ◽  
Yuukou HORITA
Keyword(s):  
Evaluation Model ◽  
Vehicle Detection ◽  
Ground Truth ◽  
Detection Evaluation

Evaluation of Commercial Truck Parking Detection for Rest Areas

2018 ◽  
Vol 2672 (9) ◽  
pp. 141-151
Author(s):  
Wei Sun ◽  
Ethan Stoop ◽  
Scott S. Washburn
Keyword(s):  
Software Tool ◽  
Vehicle Detection ◽  
Ground Truth ◽  
Early Morning ◽  
Video Data ◽  
Sensor Data ◽  
Parking Space ◽  
Ground Truth Data ◽  
Detection Technology ◽  
Rest Areas

Florida’s interstate rest areas are heavily utilized by commercial trucks for overnight parking. Many of these rest areas regularly experience 100% utilization of available commercial truck parking spaces during the evening and early-morning hours. Being able to communicate availability of commercial truck parking space to drivers in advance of arriving at a rest area would reduce unnecessary stops at full rest areas as well as driver anxiety. In order to do this, it is critical to implement a vehicle detection technology to reflect the parking status of the rest area correctly. The objective of this project was to evaluate three different wireless in-pavement vehicle detection technologies as applied to commercial truck parking at interstate rest areas. This paper mainly focuses on the following aspects: (a) accuracy of the vehicle detection in parking spaces, (b) installation, setup, and maintenance of the vehicle detection technology, and (c) truck parking trends at the rest area study site. The final project report includes a more detailed summary of the evaluation. The research team recorded video of the rest areas as the ground-truth data and developed a software tool to compare the video data with the parking sensor data. Two accuracy tests (event accuracy and occupancy accuracy) were conducted to evaluate each sensor’s ability to reflect the status of each parking space correctly. Overall, it was found that all three technologies performed well, with accuracy rates of 95% or better for both tests. This result suggests that, for implementation, pricing, and/or maintenance issues may be more significant factors for the choice of technology.

Expanding the Capabilities of Radar-Based Vehicle Detection Systems: Noise Characterization and Removal Procedures

2019 ◽  
Vol 2673 (11) ◽  
pp. 150-160
Author(s):  
Kelvin R. Santiago-Chaparro ◽  
David A. Noyce
Keyword(s):  
Performance Measures ◽  
Vehicle Detection ◽  
Ground Truth ◽  
Noise Removal ◽  
Performance Measure ◽  
Signalized Intersections ◽  
Volume Data ◽  
Trajectory Data ◽  
Potential Accuracy ◽  
Detection Systems

The capabilities of radar-based vehicle detection (RVD) systems used at signalized intersections for stop bar and advanced detection are arguably underutilized. Underutilization happens because RVD systems can monitor the position and speed (i.e., trajectory) of multiple vehicles at the same time but these trajectories are only used to emulate the behavior of legacy detection systems such as inductive loop detectors. When full vehicle trajectories tracked by an RVD system are collected, detailed traffic operations and safety performance measures can be calculated for signalized intersections. Unfortunately, trajectory datasets obtained from RVD systems often contain significant noise which makes the computation of performance measures difficult. In this paper, a description of the type of trajectory datasets that can be obtained from RVD systems is presented along with a characterization of the noise expected in these datasets. Guidance on the noise removal procedures that can be applied to these datasets is also presented. This guidance can be applied to the use of data from commercially-available RVD systems to obtain advanced performance measures. To demonstrate the potential accuracy of the noise removal procedures, the procedures were applied to trajectory data obtained from an existing intersection, and data on a basic performance measure (vehicle volume) were extracted from the dataset. Volume data derived from the de-noised trajectory dataset was compared with ground truth volume and an absolute average difference of approximately one vehicle every 5 min was found, thus highlighting the potential accuracy of the noise removal procedures introduced.

Research on Openflow Application in Intrusion Detection Evaluation

2014 ◽  
Vol 602-605 ◽  
pp. 1908-1911
Author(s):  
Qing Tian ◽  
Jun Ling Zhu
Keyword(s):  
Intrusion Detection ◽  
Program Implementation ◽  
Evaluation System ◽  
Evaluation Model ◽  
Real Data ◽  
Network Control ◽  
Experimental Result ◽  
Model Based ◽  
Data Source ◽  
Detection Evaluation

Based on the data source problems of intrusion detection evaluation and the feature of OpenFlow capable of providing flexible network control, this paper studies the real data evaluation model based on the software-defined network, and makes program implementation over the model-based intrusion detection evaluation system, and then uses the network to simulate this model. The experimental result shows that the model is feasible and effective.

scholarly journals Vehicle Detection and Type Classification Based on CNN-SVM

2021 ◽  
Vol 11 (4) ◽  
pp. 304-310
Author(s):  
Stephen Karungaru ◽  
◽  
Lyu Dongyang ◽  
Kenji Terada
Keyword(s):  
Vehicle Detection ◽  
Ground Truth ◽  
Vehicle Classification ◽  
Neural Network Learning ◽  
Single Feature ◽  
Spatial Pyramid Pooling ◽  
Model Size ◽  
Candidate Regions ◽  
Optimal Feature ◽  
Type Classification

In this paper, we propose vehicle detection and classification in a real road environment using a modified and improved AlexNet. Among the various challenges faced, the problem of poor robustness in extracting vehicle candidate regions through a single feature is solved using the YOLO deep learning series algorithm used to propose potential regions and to further improve the speed of detection. For this, the lightweight network Yolov2-tiny is chosen as the location network. In the training process, anchor box clustering is performed based on the ground truth of the training set, which improves its performance on the specific dataset. The low classification accuracy problem after template-based feature extraction is solved using the optimal feature description extracted through convolution neural network learning. Moreover, based on AlexNet, through adjusting parameters, an improved algorithm was proposed whose model size is smaller and classification speed is faster than the original AlexNet. Spatial Pyramid Pooling (SPP) is added to the vehicle classification network which solves the problem of low accuracy due to image distortion caused by image resizing. By combining CNN with SVM and normalizing features in SVM, the generalization ability of the model was improved. Experiments show that our method has a better performance in vehicle detection and type classification.

scholarly journals Small-Sized Vehicle Detection in Remote Sensing Image Based on Keypoint Detection

2021 ◽  
Vol 13 (21) ◽  
pp. 4442
Author(s):  
Lijian Yu ◽  
Xiyang Zhi ◽  
Jianming Hu ◽  
Shikai Jiang ◽  
Wei Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Aspect Ratio ◽  
Deep Layer ◽  
Vehicle Detection ◽  
Ground Truth ◽  
Remote Sensing Image ◽  
Detection Task ◽  
Small Object ◽  
Remote Sensing Images ◽  
Distribution Strategy

The vehicle detection in remote sensing images is a challenging task due to the small size of the objects and interference of a complex background. Traditional methods require a large number of anchor boxes, and the intersection rate between these anchor boxes and an object's real position boxes needs to be high enough. Moreover, the size and aspect ratio of each anchor box need to be designed manually. For small objects, more anchor boxes need to be set. To solve these problems, we regard the small object as a keypoint in the relevant background and propose an anchor-free vehicle detection network (AVD-kpNet) to robustly detect small-sized vehicles in remote sensing images. The AVD-kpNet framework fuses features across layers with a deep layer aggregation architecture, preserving the fine features of small objects. First, considering the correlation between the object and the surrounding background, a 2D Gaussian distribution strategy is adopted to describe the ground truth, instead of a hard label approach. Moreover, we redesign the corresponding focus loss function. Experimental results demonstrate that our method has a higher accuracy for the small-sized vehicle detection task in remote sensing images compared with several advanced methods.

scholarly journals COMAP: A SYNTHETIC DATASET FOR COLLECTIVE MULTI-AGENT PERCEPTION OF AUTONOMOUS DRIVING

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 255-263
Author(s):  
Y. Yuan ◽  
M. Sester
Keyword(s):  
Synthetic Data ◽  
Simulated Data ◽  
Vehicle Detection ◽  
Ground Truth ◽  
Autonomous Driving ◽  
Superior Performance ◽  
Detection Accuracy ◽  
Data Set ◽  
Cloud Data ◽  
Data Generator

Abstract. Collective perception of connected vehicles can sufficiently increase the safety and reliability of autonomous driving by sharing perception information. However, collecting real experimental data for such scenarios is extremely expensive. Therefore, we built a computational efficient co-simulation synthetic data generator through CARLA and SUMO simulators. The simulated data contain image and point cloud data as well as ground truth for object detection and semantic segmentation tasks. To verify the superior performance gain of collective perception over single-vehicle perception, we conducted experiments of vehicle detection, which is one of the most important perception tasks for autonomous driving, on this data set. A 3D object detector and a Bird’s Eye View (BEV) detector are trained and then test with different configurations of the number of cooperative vehicles and vehicle communication ranges. The experiment results showed that collective perception can not only dramatically increase the overall mean detection accuracy but also the localization accuracy of detected bounding boxes. Besides, a vehicle detection comparison experiment showed that the detection performance drop caused by sensor observation noise can be canceled out by redundant information collected by multiple vehicles.

scholarly journals Vehicle Detection Using Deep Learning Technique in Tunnel Road Environments

Symmetry ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 2012
Author(s):  
JongBae Kim
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Detection Method ◽  
Vehicle Detection ◽  
Ground Truth ◽  
Noise Removal ◽  
Detection Accuracy ◽  
Vehicle Exhaust ◽  
Learning Techniques ◽  
Real Time Detection

This paper proposes a real-time detection method for a car driving ahead in real time on a tunnel road. Unlike the general road environment, the tunnel environment is irregular and has significantly lower illumination, including tunnel lighting and light reflected from driving vehicles. The environmental restrictions are large owing to pollution by vehicle exhaust gas. In the proposed method, a real-time detection method is used for vehicles in tunnel images learned in advance using deep learning techniques. To detect the vehicle region in the tunnel environment, brightness smoothing and noise removal processes are carried out. The vehicle region is learned after generating a learning image using the ground-truth method. The YOLO v2 model, with an optimal performance compared to the performances of deep learning algorithms, is applied. The training parameters are refined through experiments. The vehicle detection rate is approximately 87%, while the detection accuracy is approximately 94% for the proposed method applied to various tunnel road environments.

Moving From Interprofessional Education Toward Interprofessional Practice: Bridging the Translation Gap

2019 ◽  
Vol 4 (5) ◽  
pp. 971-976
Author(s):  
Imran Musaji ◽  
Trisha Self ◽  
Karissa Marble-Flint ◽  
Ashwini Kanade
Keyword(s):  
Interprofessional Education ◽  
Interprofessional Collaboration ◽  
Evaluation Model ◽  
Implementation Strategies ◽  
Future Research ◽  
Successful Implementation ◽  
Interprofessional Practice ◽  
Translational Model ◽  
Key Stakeholders ◽  
Clear Identification

Purpose The purpose of this article was to propose the use of a translational model as a tool for identifying limitations of current interprofessional education (IPE) research. Translational models allow researchers to clearly define next-step research needed to translate IPE to interprofessional practice (IPP). Method Key principles, goals, and limitations of current IPE research are reviewed. A popular IPE evaluation model is examined through the lens of implementation research. The authors propose a new translational model that more clearly illustrates translational gaps that can be used to direct future research. Next steps for translating IPE to IPP are discussed. Conclusion Comprehensive reviews of the literature show that the implementation strategies adopted to date have fostered improved buy-in from key stakeholders, as evidenced by improved attitudes and perceptions toward interprofessional collaboration/practice. However, there is little evidence regarding successful implementation outcomes, such as changed clinician behaviors, changed organizational practices, or improved patient outcomes. The authors propose the use of an IPE to IPP translational model to facilitate clear identification of research gaps and to better identify future research targets.

A Comparison of Simple Structure Rotation Criteria in Temporal Exploratory Factor Analysis for Event-Related Potential Data

Methodology ◽  
2019 ◽  
Vol 15 (Supplement 1) ◽  
pp. 43-60 ◽  
Author(s):  
Florian Scharf ◽  
Steffen Nestler
Keyword(s):  
Factor Analysis ◽  
Exploratory Factor Analysis ◽  
Simple Structure ◽  
Ground Truth ◽  
Event Related Potential ◽  
Suitable Alternative ◽  
Factor Rotation ◽  
Rotation Methods ◽  
Simple Structure Rotation ◽  
Temporal Overlap

Abstract. It is challenging to apply exploratory factor analysis (EFA) to event-related potential (ERP) data because such data are characterized by substantial temporal overlap (i.e., large cross-loadings) between the factors, and, because researchers are typically interested in the results of subsequent analyses (e.g., experimental condition effects on the level of the factor scores). In this context, relatively small deviations in the estimated factor solution from the unknown ground truth may result in substantially biased estimates of condition effects (rotation bias). Thus, in order to apply EFA to ERP data researchers need rotation methods that are able to both recover perfect simple structure where it exists and to tolerate substantial cross-loadings between the factors where appropriate. We had two aims in the present paper. First, to extend previous research, we wanted to better understand the behavior of the rotation bias for typical ERP data. To this end, we compared the performance of a variety of factor rotation methods under conditions of varying amounts of temporal overlap between the factors. Second, we wanted to investigate whether the recently proposed component loss rotation is better able to decrease the bias than traditional simple structure rotation. The results showed that no single rotation method was generally superior across all conditions. Component loss rotation showed the best all-round performance across the investigated conditions. We conclude that Component loss rotation is a suitable alternative to simple structure rotation. We discuss this result in the light of recently proposed sparse factor analysis approaches.

Sign in / Sign up

Export Citation Format

Share Document