scholarly journals Uncertainty Evaluation of Object Detection Algorithms for Autonomous Vehicles

2021 ◽  
Author(s):  
Liang Peng ◽  
Hong Wang ◽  
Jun Li
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Confusion Matrix ◽  
Autonomous Driving ◽  
Detection Algorithm ◽  
Risk Identification ◽  
Practical Implementation ◽  
Complex Object ◽  
Detection Algorithms ◽  
Online Risk

AbstractThe safety of the intended functionality (SOTIF) has become one of the hottest topics in the field of autonomous driving. However, no testing and evaluating system for SOTIF performance has been proposed yet. Therefore, this paper proposes a framework based on the advanced You Only Look Once (YOLO) algorithm and the mean Average Precision (mAP) method to evaluate the object detection performance of the camera under SOTIF-related scenarios. First, a dataset is established, which contains road images with extreme weather and adverse lighting conditions. Second, the Monte Carlo dropout (MCD) method is used to analyze the uncertainty of the algorithm and draw the uncertainty region of the predicted bounding box. Then, the confidence of the algorithm is calibrated based on uncertainty results so that the average confidence after calibration can better reflect the real accuracy. The uncertainty results and the calibrated confidence are proposed to be used for online risk identification. Finally, the confusion matrix is extended according to the several possible mistakes that the object detection algorithm may make, and then the mAP is calculated as an index for offline evaluation and comparison. This paper offers suggestions to apply the MCD method to complex object detection algorithms and to find the relationship between the uncertainty and the confidence of the algorithm. The experimental results verified by specific SOTIF scenarios proof the feasibility and effectiveness of the proposed uncertainty acquisition approach for object detection algorithm, which provides potential practical implementation chance to address perceptual related SOTIF risk for autonomous vehicles.

scholarly journals A Set of Single YOLO Modalities to Detect Occluded Entities via Viewpoint Conversion

2021 ◽  
Vol 11 (13) ◽  
pp. 6016
Author(s):  
Jinsoo Kim ◽  
Jeongho Cho
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Autonomous Driving ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Cloud Data ◽  
Detection Techniques ◽  
Bounding Boxes ◽  
Partially Occluded ◽  
Rgb Image

For autonomous vehicles, it is critical to be aware of the driving environment to avoid collisions and drive safely. The recent evolution of convolutional neural networks has contributed significantly to accelerating the development of object detection techniques that enable autonomous vehicles to handle rapid changes in various driving environments. However, collisions in an autonomous driving environment can still occur due to undetected obstacles and various perception problems, particularly occlusion. Thus, we propose a robust object detection algorithm for environments in which objects are truncated or occluded by employing RGB image and light detection and ranging (LiDAR) bird’s eye view (BEV) representations. This structure combines independent detection results obtained in parallel through “you only look once” networks using an RGB image and a height map converted from the BEV representations of LiDAR’s point cloud data (PCD). The region proposal of an object is determined via non-maximum suppression, which suppresses the bounding boxes of adjacent regions. A performance evaluation of the proposed scheme was performed using the KITTI vision benchmark suite dataset. The results demonstrate the detection accuracy in the case of integration of PCD BEV representations is superior to when only an RGB camera is used. In addition, robustness is improved by significantly enhancing detection accuracy even when the target objects are partially occluded when viewed from the front, which demonstrates that the proposed algorithm outperforms the conventional RGB-based model.

A dual U-Net algorithm for automating feature extraction from satellite imagery

2021 ◽  
pp. 154851292098354
Author(s):  
Samuel Humphries ◽  
Trevor Parker ◽  
Bryan Jonas ◽  
Bryan Adams ◽  
Nicholas J Clark
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Satellite Images ◽  
Detection Algorithm ◽  
Military Operations ◽  
Detection Algorithms ◽  
Us Military ◽  
Standard Product ◽  
Different Types ◽  
Road Intersections

Quick identification of building and roads is critical for execution of tactical US military operations in an urban environment. To this end, a gridded, referenced, satellite images of an objective, often referred to as a gridded reference graphic or GRG, has become a standard product developed during intelligence preparation of the environment. At present, operational units identify key infrastructure by hand through the work of individual intelligence officers. Recent advances in Convolutional Neural Networks, however, allows for this process to be streamlined through the use of object detection algorithms. In this paper, we describe an object detection algorithm designed to quickly identify and label both buildings and road intersections present in an image. Our work leverages both the U-Net architecture as well the SpaceNet data corpus to produce an algorithm that accurately identifies a large breadth of buildings and different types of roads. In addition to predicting buildings and roads, our model numerically labels each building by means of a contour finding algorithm. Most importantly, the dual U-Net model is capable of predicting buildings and roads on a diverse set of test images and using these predictions to produce clean GRGs.

scholarly journals Deep Learning Object Detector Using a Combination of Convolutional Neural Network (CNN) Architecture (MiniVGGNet) and Classic Object Detection Algorithm

2020 ◽  
Vol 28 (S2) ◽  
Author(s):  
Asmida Ismail ◽  
Siti Anom Ahmad ◽  
Azura Che Soh ◽  
Mohd Khair Hassan ◽  
Hazreen Haizi Harith
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Detection System ◽  
Object Classification ◽  
Detection Algorithm ◽  
Learning Object ◽  
Sliding Windows ◽  
Detection Algorithms

The object detection system is a computer technology related to image processing and computer vision that detects instances of semantic objects of a certain class in digital images and videos. The system consists of two main processes, which are classification and detection. Once an object instance has been classified and detected, it is possible to obtain further information, including recognizes the specific instance, track the object over an image sequence and extract further information about the object and the scene. This paper presented an analysis performance of deep learning object detector by combining a deep learning Convolutional Neural Network (CNN) for object classification and applies classic object detection algorithms to devise our own deep learning object detector. MiniVGGNet is an architecture network used to train an object classification, and the data used for this purpose was collected from specific indoor environment building. For object detection, sliding windows and image pyramids were used to localize and detect objects at different locations, and non-maxima suppression (NMS) was used to obtain the final bounding box to localize the object location. Based on the experiment result, the percentage of classification accuracy of the network is 80% to 90% and the time for the system to detect the object is less than 15sec/frame. Experimental results show that there are reasonable and efficient to combine classic object detection method with a deep learning classification approach. The performance of this method can work in some specific use cases and effectively solving the problem of the inaccurate classification and detection of typical features.

scholarly journals Dynamic Object Detection Algorithm Based on Lightweight Shared Feature Pyramid

2021 ◽  
Vol 13 (22) ◽  
pp. 4610
Author(s):  
Li Zhu ◽  
Zihao Xie ◽  
Jing Luo ◽  
Yuhang Qi ◽  
Liman Liu ◽  
...  
Keyword(s):  
Object Detection ◽  
Feature Fusion ◽  
Computational Cost ◽  
Detection Algorithm ◽  
Dynamic Object ◽  
Shared Feature ◽  
Detection Model ◽  
Detection Algorithms ◽  
Adaptive Inference ◽  
Feature Pyramid

Current object detection algorithms perform inference on all samples at a fixed computational cost in the inference stage, which wastes computing resources and is not flexible. To solve this problem, a dynamic object detection algorithm based on a lightweight shared feature pyramid is proposed, which performs adaptive inference according to computing resources and the difficulty of samples, greatly improving the efficiency of inference. Specifically, a lightweight shared feature pyramid network and lightweight detection head is proposed to reduce the amount of computation and parameters in the feature fusion part and detection head of the dynamic object detection model. On the PASCAL VOC dataset, under the two conditions of “anytime prediction” and “budgeted batch object detection”, the performance, computation amount and parameter amount are better than the dynamic object detection models constructed by networks such as ResNet, DenseNet and MSDNet.

scholarly journals Object Detection in Autonomous Driving Scenarios Based on an Improved Faster-RCNN

2021 ◽  
Vol 11 (24) ◽  
pp. 11630
Author(s):  
Yan Zhou ◽  
Sijie Wen ◽  
Dongli Wang ◽  
Jinzhen Mu ◽  
Irampaye Richard
Keyword(s):  
Object Detection ◽  
Autonomous Driving ◽  
Detection Algorithm ◽  
Data Sets ◽  
False Detection ◽  
Automatic Driving ◽  
Occluded Objects ◽  
Pyramid Structure ◽  
Feature Pyramid ◽  
Bounding Boxes

Object detection is one of the key algorithms in automatic driving systems. Aiming at addressing the problem of false detection and the missed detection of both small and occluded objects in automatic driving scenarios, an improved Faster-RCNN object detection algorithm is proposed. First, deformable convolution and a spatial attention mechanism are used to improve the ResNet-50 backbone network to enhance the feature extraction of small objects; then, an improved feature pyramid structure is introduced to reduce the loss of features in the fusion process. Three cascade detectors are introduced to solve the problem of IOU (Intersection-Over-Union) threshold mismatch, and side-aware boundary localization is applied for frame regression. Finally, Soft-NMS (Soft Non-maximum Suppression) is used to remove bounding boxes to obtain the best results. The experimental results show that the improved Faster-RCNN can better detect small objects and occluded objects, and its accuracy is 7.7% and 4.1% respectively higher than that of the baseline in the eight categories selected from the COCO2017 and BDD100k data sets.

scholarly journals X-Ray Image Recognition Based on Improved Mask R-CNN Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Jicun Zhang ◽  
Xueping Song ◽  
Jiawei Feng ◽  
Jiyou Fei
Keyword(s):  
Object Detection ◽  
Lower Layer ◽  
Detection Algorithm ◽  
Intelligent Manufacturing ◽  
Average Precision ◽  
X Ray ◽  
Detection Algorithms ◽  
Security Inspection ◽  
Scale Difference ◽  
The Stability

It is an important part of security inspection to carry out security and safety screening with X-ray scanners. Computer vision plays an important role in detection, recognition, and location analysis in intelligent manufacturing. The object detection algorithm is an important part of the intelligent X-ray machine. Existing threat object detection algorithms in X-ray images have low detection precision and are prone to missed and false detection. In order to increase the precision, a new improved Mask R-CNN algorithm is proposed in this paper. In the feature extraction network, an enhancement path is added to fuse the features of the lower layer into the higher layer, which reduces the loss of feature information. By adding an edge detection module, the training effect of the sample model can be improved without accurate labeling. The distance, overlap rate, and scale difference between objects and region proposals are solved using DIoU to improve the stability of the region proposal’s regression, thus improving the accuracy of object detection; SoftNMS algorithm is used to overcome the problem of missed detection when the objects to be detected overlap each other. The experimental results indicate that the mean Average Precision (mAP) of the improved algorithm is 9.32% higher than that of the Mask R-CNN algorithm, especially for knife and portable batteries, which are small in size, simple in shape, and easy to be mistakenly detected, and the Average Precision (AP) is increased by 13.41% and 15.92%, respectively. The results of the study have important implications for the practical application of threat object detection in X-ray images.

scholarly journals Free Space Detection Algorithm Using Object Tracking for Autonomous Vehicles

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 315
Author(s):  
Yeongwon Lee ◽  
Byungyong You
Keyword(s):  
Object Tracking ◽  
Dynamic Behavior ◽  
Free Space ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Detection Algorithm ◽  
Location Information ◽  
Classification Result ◽  
Detection Algorithms ◽  
Previous Algorithm

In this paper, we propose a new free space detection algorithm for autonomous vehicle driving. Previous free space detection algorithms often use only the location information of every frame, without information on the speed of the obstacle. In this case, there is a possibility of creating an inefficient path because the behavior of the obstacle cannot be predicted. In order to compensate for the shortcomings of the previous algorithm, the proposed algorithm uses the speed information of the obstacle. Through object tracking, the dynamic behavior of obstacles around the vehicle is identified and predicted, and free space is detected based on this. In the free space, it is possible to classify an area in which driving is possible and an area in which it is not possible, and a route is created according to the classification result. By comparing and evaluating the path generated by the previous algorithm and the path generated by the proposed algorithm, it is confirmed that the proposed algorithm is more efficient in generating the vehicle driving path.

scholarly journals Parallel tracking and detection for long-term object tracking

2020 ◽  
Vol 17 (2) ◽  
pp. 172988142090257
Author(s):  
Dan Xiong ◽  
Huimin Lu ◽  
Qinghua Yu ◽  
Junhao Xiao ◽  
Wei Han ◽  
...  
Keyword(s):  
Object Detection ◽  
Object Tracking ◽  
Detection Algorithm ◽  
Detection Algorithms ◽  
Art Object ◽  
High Processing Speed ◽  
Online Learning Algorithms ◽  
Integrate State ◽  
Unknown Object

High tracking frame rates have been achieved based on traditional tracking methods which however would fail due to drifts of the object template or model, especially when the object disappears from the camera’s field of view. To deal with it, tracking-and-detection-combination has become more and more popular for long-term unknown object tracking, whose detector almost does not drift and can regain the disappeared object when it comes back. However, for online machine learning and multiscale object detection, expensive computing resources and time are required. So it is not a good idea to combine tracking and detection sequentially like Tracking-Learning-Detection algorithm. Inspired from parallel tracking and mapping, this article proposes a framework of parallel tracking and detection for unknown object tracking. The object tracking algorithm is split into two separate tasks—tracking and detection which can be processed in two different threads, respectively. One thread is used to deal with the tracking between consecutive frames with a high processing speed. The other thread runs online learning algorithms to construct a discriminative model for object detection. Using our proposed framework, high tracking frame rates and the ability of correcting and recovering the failed tracker can be combined effectively. Furthermore, our framework provides open interfaces to integrate state-of-the-art object tracking and detection algorithms. We carry out an evaluation of several popular tracking and detection algorithms using the proposed framework. The experimental results show that different tracking and detection algorithms can be integrated and compared effectively by our proposed framework, and robust and fast long-term object tracking can be realized.

scholarly journals Identification and Explanation of Challenging Conditions for Camera-Based Object Detection of Automated Vehicles

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3699 ◽  
Author(s):  
Thomas Ponn ◽  
Thomas Kröger ◽  
Frank Diermeyer
Keyword(s):  
Artificial Intelligence ◽  
Object Detection ◽  
Influence Factors ◽  
Detection Algorithm ◽  
Detection Performance ◽  
Automated Vehicles ◽  
Detection Algorithms ◽  
Type Approval ◽  
Market Launch ◽  
First Time

For a safe market launch of automated vehicles, the risks of the overall system as well as the sub-components must be efficiently identified and evaluated. This also includes camera-based object detection using artificial intelligence algorithms. It is trivial and explainable that due to the principle of the camera, performance depends highly on the environmental conditions and can be poor, for example in heavy fog. However, there are other factors influencing the performance of camera-based object detection, which will be comprehensively investigated for the first time in this paper. Furthermore, a precise modeling of the detection performance and the explanation of individual detection results is not possible due to the artificial intelligence based algorithms used. Therefore, a modeling approach based on the investigated influence factors is proposed and the newly developed SHapley Additive exPlanations (SHAP) approach is adopted to analyze and explain the detection performance of different object detection algorithms. The results show that many influence factors such as the relative rotation of an object towards the camera or the position of an object on the image have basically the same influence on the detection performance regardless of the detection algorithm used. In particular, the revealed weaknesses of the tested object detectors can be used to derive challenging and critical scenarios for the testing and type approval of automated vehicles.

Sign in / Sign up

Export Citation Format

Share Document