Vehicle Detection and Speed Tracking Based on Object Detection

2020 ◽  
pp. 403-409
Author(s):  
Gaurav Dubey ◽  
Ayush Tiwari ◽  
Akash Singh ◽  
Aryan Upadhyay
Keyword(s):  
Object Detection ◽  
Vehicle Detection ◽  
Speed Tracking

scholarly journals DAR-Net: Dense Attentional Residual Network for Vehicle Detection in Aerial Images

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Kaifeng Li ◽  
Bin Wang
Keyword(s):  
Object Detection ◽  
Information Flow ◽  
Spatial Information ◽  
Rapid Development ◽  
Vehicle Detection ◽  
Aerial Images ◽  
Feature Maps ◽  
Residual Network ◽  
General Object ◽  
The Impact

With the rapid development of deep learning and the wide usage of Unmanned Aerial Vehicles (UAVs), CNN-based algorithms of vehicle detection in aerial images have been widely studied in the past several years. As a downstream task of the general object detection, there are some differences between the vehicle detection in aerial images and the general object detection in ground view images, e.g., larger image areas, smaller target sizes, and more complex background. In this paper, to improve the performance of this task, a Dense Attentional Residual Network (DAR-Net) is proposed. The proposed network employs a novel dense waterfall residual block (DW res-block) to effectively preserve the spatial information and extract high-level semantic information at the same time. A multiscale receptive field attention (MRFA) module is also designed to select the informative feature from the feature maps and enhance the ability of multiscale perception. Based on the DW res-block and MRFA module, to protect the spatial information, the proposed framework adopts a new backbone that only downsamples the feature map 3 times; i.e., the total downsampling ratio of the proposed backbone is 8. These designs could alleviate the degradation problem, improve the information flow, and strengthen the feature reuse. In addition, deep-projection units are used to reduce the impact of information loss caused by downsampling operations, and the identity mapping is applied to each stage of the proposed backbone to further improve the information flow. The proposed DAR-Net is evaluated on VEDAI, UCAS-AOD, and DOTA datasets. The experimental results demonstrate that the proposed framework outperforms other state-of-the-art algorithms.

scholarly journals Optimized loss functions for object detection and application on nighttime vehicle detection

2021 ◽  
pp. 095440702110363
Author(s):  
Shang Jiang ◽  
Haoran Qin ◽  
Bingli Zhang ◽  
Jieyu Zheng
Keyword(s):  
Object Detection ◽  
Loss Function ◽  
Mahalanobis Distance ◽  
Vehicle Detection ◽  
Detection Task ◽  
Loss Functions ◽  
Detection Accuracy ◽  
Localization Accuracy ◽  
Detection Speed

The loss function is a crucial factor that affects the detection precision in the object detection task. In this paper, we optimize both two loss functions for classification and localization simultaneously. Firstly, we reconstruct the classification loss function by combining the prediction results of localization, aiming to establish the correlation between localization and classification subnetworks. Compared to the existing studies, in which the correlation is only established among the positive samples and applied to improve the localization accuracy of predicted boxes, this paper utilizes the correlation to define the hard negative samples and then puts emphasis on the classification of them. Thus the whole misclassified rate for negative samples can be reduced. Besides, a novel localization loss named MIoU is proposed by incorporating a Mahalanobis distance between the predicted box and target box, eliminating the gradients inconsistency problem in the DIoU loss, further improving the localization accuracy. Finally, the proposed methods are applied to train the networks for nighttime vehicle detection. Experimental results show that the detection accuracy can be outstandingly improved with our proposed loss functions without hurting the detection speed.

scholarly journals Comparison Of Cellular Video Quality For Object Detection Using Neural Network Convolution

SinkrOn ◽  
2019 ◽  
Vol 4 (1) ◽  
pp. 260 ◽  
Author(s):  
Kevin Kevin ◽  
Nico Gunawan ◽  
Mariana Erfan Kristiani Zagoto ◽  
Laurentius Laurentius ◽  
Amir Mahmud Husein
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Real Time ◽  
Video Quality ◽  
Vehicle Detection ◽  
Neural Network Method ◽  
Network Method ◽  
Object Of Study ◽  
Capture Capacity ◽  
Detection And Recognition

Abstract— The purpose of this study is to compare the video quality between the Samsung HP camera and the Xiaomi HP camera. The object of study was UNPRI students who walked through the front yard of the UNPRI SEKIP campus. Here we test how accurate the camera's HP capture capacity is used to take the video. The method used to test this research is the Convolution Neural Network method. Object detection and recognition aim to detect and classify objects that can be applied to various fields such as face, human, pedestrian, vehicle detection (Pedoeem & Huang, 2018), besides the ability to find, identify, track and stabilize objects in various poses and important backgrounds in many real-time video applications. Object detection, tracking, alignment and stabilization have become very interesting fields of research in the vision and recognition of computer patterns due to the challenging nature of several slightly different objects such as object detection, where the algorithm must be precise enough to identify, track and center an object from the others

scholarly journals Vehicle Detection and Traffic Prediction

2021 ◽  
Vol 9 (9) ◽  
pp. 1791-1794
Author(s):  
Ms. Aysha
Keyword(s):  
Linear Regression ◽  
Object Detection ◽  
Multiple Linear Regression ◽  
Police Officers ◽  
Traffic Control ◽  
Vehicle Detection ◽  
Vehicle Speed ◽  
The Road ◽  
On The Road ◽  
Control Traffic

Abstract: On the road, vehicle detection processes are utilized for vehicle tracking, vehicle counting, vehicle speed, and traffic analysis. For vehicle detection, the Tensorflow object detection API method is employed. The Object Detection API in Tensorflow is a powerful tool that allows anyone to easily design and deploy effective picture recognition applications. Another way to control traffic is to use a traffic control system. Multiple linear regression is utilized to regulate the traffic system, while the OpenCV approach is used to identify vehicle speed. A system for fine payment is also offered. It makes police officers' jobs easier. The exact results of vehicle speed and traffic control are provided. Keywords: Vehicle detection, Tensorflow object detection API, Multiple linear regression, OpenCV, Fine payment

scholarly journals Boosting Multi-Vehicle Tracking with a Joint Object Detection and Viewpoint Estimation Sensor

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4062 ◽  
Author(s):  
Roberto López-Sastre ◽  
Carlos Herranz-Perdiguero ◽  
Ricardo Guerrero-Gómez-Olmedo ◽  
Daniel Oñoro-Rubio ◽  
Saturnino Maldonado-Bascón
Keyword(s):  
Object Detection ◽  
Vehicle Detection ◽  
Traffic Monitoring ◽  
Vehicle Tracking ◽  
Object Localization ◽  
Support Vector ◽  
Detection And Tracking ◽  
Vehicle Detection And Tracking ◽  
Monitoring Applications ◽  
Viewpoint Estimation

In this work, we address the problem of multi-vehicle detection and tracking for traffic monitoring applications. We preset a novel intelligent visual sensor for tracking-by-detection with simultaneous pose estimation. Essentially, we adapt an Extended Kalman Filter (EKF) to work not only with the detections of the vehicles but also with their estimated coarse viewpoints, directly obtained with the vision sensor. We show that enhancing the tracking with observations of the vehicle pose, results in a better estimation of the vehicles trajectories. For the simultaneous object detection and viewpoint estimation task, we present and evaluate two independent solutions. One is based on a fast GPU implementation of a Histogram of Oriented Gradients (HOG) detector with Support Vector Machines (SVMs). For the second, we adequately modify and train the Faster R-CNN deep learning model, in order to recover from it not only the object localization but also an estimation of its pose. Finally, we publicly release a challenging dataset, the GRAM Road Traffic Monitoring (GRAM-RTM), which has been especially designed for evaluating multi-vehicle tracking approaches within the context of traffic monitoring applications. It comprises more than 700 unique vehicles annotated across more than 40.300 frames of three videos. We expect the GRAM-RTM becomes a benchmark in vehicle detection and tracking, providing the computer vision and intelligent transportation systems communities with a standard set of images, annotations and evaluation procedures for multi-vehicle tracking. We present a thorough experimental evaluation of our approaches with the GRAM-RTM, which will be useful for establishing further comparisons. The results obtained confirm that the simultaneous integration of vehicle localizations and pose estimations as observations in an EKF, improves the tracking results.

scholarly journals Satellite Imagery Classification with Deep Learning : A Survey

2020 ◽  
pp. 36-46
Author(s):  
Niharika Goswami ◽  
Keyurkumar Kathiriya ◽  
Santosh Yadav ◽  
Janki Bhatt ◽  
Sheshang Degadwala
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Object Detection ◽  
Satellite Imagery ◽  
Satellite Images ◽  
Weather Forecasting ◽  
Vehicle Detection ◽  
Suitable Alternative ◽  
High Resolution Satellite Images ◽  
Technological Developments

Object detection from satellite images has been a challenging problem for many years. With the development of effective deep learning algorithms and advancement in hardware systems, higher accuracies have been achieved in the detection of various objects from very high-resolution satellite images. In the past decades satellite imagery has been used successfully for weather forecasting, geographical and geological applications. Low resolution satellite images are sufficient for these sorts of applications. But the technological developments in the field of satellite imaging provide high resolution sensors which expands its field of application. Thus, the High-Resolution Satellite Imagery (HRSI) proved to be a suitable alternative to aerial photogrammetric data to provide a new data source for object detection. Since the traffic rates in developing countries are enormously increasing, vehicle detection from satellite data will be a better choice for automating such systems. In this research, a different technique for vehicle detection from the images obtained from high resolution sensors is reviewed. This review presents the recent progress in the field of object detection from satellite imagery using deep learning.

scholarly journals A Deep-Learning-Based Vehicle Detection Approach for Insufficient and Nighttime Illumination Conditions

2019 ◽  
Vol 9 (22) ◽  
pp. 4769 ◽  
Author(s):  
Ho Kwan Leung ◽  
Xiu-Zhi Chen ◽  
Chao-Wei Yu ◽  
Hong-Yi Liang ◽  
Jian-Yi Wu ◽  
...  
Keyword(s):  
Object Detection ◽  
Vehicle Detection ◽  
Fixed Number ◽  
Detection Performance ◽  
Data Sets ◽  
Detection Techniques ◽  
Ambient Lighting ◽  
Occluded Objects ◽  
Detection Approach ◽  
Public Data

Most object detection models cannot achieve satisfactory performance under nighttime and other insufficient illumination conditions, which may be due to the collection of data sets and typical labeling conventions. Public data sets collected for object detection are usually photographed with sufficient ambient lighting. However, their labeling conventions typically focus on clear objects and ignore blurry and occluded objects. Consequently, the detection performance levels of traditional vehicle detection techniques are limited in nighttime environments without sufficient illumination. When objects occupy a small number of pixels and the existence of crucial features is infrequent, traditional convolutional neural networks (CNNs) may suffer from serious information loss due to the fixed number of convolutional operations. This study presents solutions for data collection and the labeling convention of nighttime data to handle various types of situations, including in-vehicle detection. Moreover, the study proposes a specifically optimized system based on the Faster region-based CNN model. The system has a processing speed of 16 frames per second for 500 × 375-pixel images, and it achieved a mean average precision (mAP) of 0.8497 in our validation segment involving urban nighttime and extremely inadequate lighting conditions. The experimental results demonstrated that our proposed methods can achieve high detection performance in various nighttime environments, such as urban nighttime conditions with insufficient illumination, and extremely dark conditions with nearly no lighting. The proposed system outperforms original methods that have an mAP value of approximately 0.2.

Sign in / Sign up

Export Citation Format

Share Document