scholarly journals Taxonomy of Object Detection methods: A Survey

2022 ◽  
Vol 10 (1) ◽  
pp. 20-25
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Real Life ◽  
Object Motion ◽  
Detection Methods ◽  
Illumination Variation ◽  
Human Machine Interaction ◽  
Research Areas ◽  
To Come ◽  
Point Detection

Object detection (OD) within a video is one of the relevant and critical research areas in the computer vision field. Due to the widespread of Artificial Intelligence, the basic principle in real life nowadays and its exponential growth predicted in the epochs to come, it will transmute the public. Object Detection has been extensively implemented in several areas, including human-machine Interaction, autonomous vehicles, security with video surveillance, and various fields that will be mentioned further. However, this augmentation of OD tackles different challenges such as occlusion, illumination variation, object motion, without ignoring the real-time aspect that can be quite problematic. This paper also includes some methods of application to take into account these issues. These techniques are divided into five subcategories: Point Detection, segmentation, supervised classifier, optical flow, a background modeling. This survey decorticates various methods and techniques used in object detection, as well as application domains and the problems faced. Our study discusses the cruciality of deep learning algorithms and their efficiency on future improvement in object detection topics within video sequences.

scholarly journals Anchor free object detection with mask attention

2020 ◽  
Author(s):  
HE Yang ◽  
Beibei Fan ◽  
Ling ling Guo
Keyword(s):  
Object Detection ◽  
Size Variation ◽  
Attention Mechanism ◽  
Detection Methods ◽  
Convolutional Network ◽  
Heat Map ◽  
Fire Model ◽  
Large Size ◽  
Map Generation ◽  
Point Detection

Abstract The anchor-free method based on key point detection has made great progress. However, the anchor-free method is too dependent on using a convolutional network to generate a rough heat map. This is difficult to detect for objects with a large size variation and dense and overlapping objects. To solve this problem, first, we propose a mask attention mechanism for object detection methods. And make full use of the advantages of the attention mechanism to improve the accuracy of network detection heat map generation. Then, we designed an optimized fire model to reduce the size of the model. The fire model is an extension of grouped convolution. The fire model allows each group of convolutional network features to learn the same feature through purposeful grouping. In this paper, the mask attention mechanism uses object segmentation images to guide the generation of corner heat maps. Our approach achieved an accuracy of 91.84% and a recall 89.83% in the Tencent-100K dataset. Compared with the popular object detection methods, the proposed method has advantages in model size and accuracy.

scholarly journals A Robust Road Vanishing Point Detection Adapted to the Real-world Driving Scenes

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2133
Author(s):  
Cuong Nguyen Khac ◽  
Yeongyu Choi ◽  
Ju H. Park ◽  
Ho-Youl Jung
Keyword(s):  
Real World ◽  
Autonomous Vehicles ◽  
Motion Vector ◽  
Ground Truth ◽  
Detection Methods ◽  
Vanishing Point ◽  
Driver Assistance Systems ◽  
Vanishing Point Detection ◽  
Edge Based ◽  
Point Detection

Vanishing point (VP) provides extremely useful information related to roads in driving scenes for advanced driver assistance systems (ADAS) and autonomous vehicles. Existing VP detection methods for driving scenes still have not achieved sufficiently high accuracy and robustness to apply for real-world driving scenes. This paper proposes a robust motion-based road VP detection method to compensate for the deficiencies. For such purposes, three main processing steps often used in the existing road VP detection methods are carefully examined. Based on the analysis, stable motion detection, stationary point-based motion vector selection, and angle-based RANSAC (RANdom SAmple Consensus) voting are proposed. A ground-truth driving dataset including various objects and illuminations is used to verify the robustness and real-time capability of the proposed method. The experimental results show that the proposed method outperforms the existing motion-based and edge-based road VP detection methods for various illumination conditioned driving scenes.

Saliency detection in deep learning era: trends of development

2019 ◽  
pp. 10-36 ◽  
Author(s):  
M. N. Favorskaya ◽  
L. C. Jain
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Event Detection ◽  
Visual Analysis ◽  
Saliency Detection ◽  
Salient Object Detection ◽  
Public Image ◽  
Detection Methods ◽  
Salient Object ◽  
Salient Event

Introduction:Saliency detection is a fundamental task of computer vision. Its ultimate aim is to localize the objects of interest that grab human visual attention with respect to the rest of the image. A great variety of saliency models based on different approaches was developed since 1990s. In recent years, the saliency detection has become one of actively studied topic in the theory of Convolutional Neural Network (CNN). Many original decisions using CNNs were proposed for salient object detection and, even, event detection.Purpose:A detailed survey of saliency detection methods in deep learning era allows to understand the current possibilities of CNN approach for visual analysis conducted by the human eyes’ tracking and digital image processing.Results:A survey reflects the recent advances in saliency detection using CNNs. Different models available in literature, such as static and dynamic 2D CNNs for salient object detection and 3D CNNs for salient event detection are discussed in the chronological order. It is worth noting that automatic salient event detection in durable videos became possible using the recently appeared 3D CNN combining with 2D CNN for salient audio detection. Also in this article, we have presented a short description of public image and video datasets with annotated salient objects or events, as well as the often used metrics for the results’ evaluation.Practical relevance:This survey is considered as a contribution in the study of rapidly developed deep learning methods with respect to the saliency detection in the images and videos.

Lattice Boltzmann for Turbulence Modeling

2018 ◽  
Author(s):  
Sauro Succi
Keyword(s):  
Turbulent Flows ◽  
Lattice Boltzmann ◽  
Turbulence Modeling ◽  
Real Life ◽  
Practical Interest ◽  
Reynolds Numbers ◽  
Full Resolution ◽  
To Come ◽  
Highly Turbulent Flows ◽  
Main Ideas

This chapter introduces the main ideas behind the application of LBE methods to the problem of turbulence modeling, namely the simulation of flows which contain scales of motion too small to be resolved on present-day and foreseeable future computers. Many real-life flows of practical interest exhibit Reynolds numbers far too high to be directly simulated in full resolution on present-day computers and arguably for many years to come. This raises the challenge of predicting the behavior of highly turbulent flows without directly simulating all scales of motion which take part to turbulence dynamics, but only those that fall within the computer resolution at hand.

Procuring cooperative intelligence in autonomous vehicles for object detection through data fusion approach

2020 ◽  
Vol 14 (11) ◽  
pp. 1410-1417 ◽  
Author(s):  
Alfred Daniel ◽  
Karthik Subburathinam ◽  
Bala Anand Muthu ◽  
Newlin Rajkumar ◽  
Seifedine Kadry ◽  
...  
Keyword(s):  
Data Fusion ◽  
Object Detection ◽  
Autonomous Vehicles ◽  
Fusion Approach

Vision-Based Navigation of Autonomous Vehicles in Roadway Environments with Unexpected Hazards

2019 ◽  
Vol 2673 (12) ◽  
pp. 494-507 ◽  
Author(s):  
Mhafuzul Islam ◽  
Mashrur Chowdhury ◽  
Hongda Li ◽  
Hongxin Hu
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Semantic Segmentation ◽  
Steering Wheel ◽  
Potential Hazard ◽  
Driving System ◽  
Hazardous Object ◽  
Vision Based Navigation ◽  
Navigational System

Vision-based navigation of autonomous vehicles primarily depends on the deep neural network (DNN) based systems in which the controller obtains input from sensors/detectors, such as cameras, and produces a vehicle control output, such as a steering wheel angle to navigate the vehicle safely in a roadway traffic environment. Typically, these DNN-based systems in the autonomous vehicle are trained through supervised learning; however, recent studies show that a trained DNN-based system can be compromised by perturbation or adverse inputs. Similarly, this perturbation can be introduced into the DNN-based systems of autonomous vehicles by unexpected roadway hazards, such as debris or roadblocks. In this study, we first introduce a hazardous roadway environment that can compromise the DNN-based navigational system of an autonomous vehicle, and produce an incorrect steering wheel angle, which could cause crashes resulting in fatality or injury. Then, we develop a DNN-based autonomous vehicle driving system using object detection and semantic segmentation to mitigate the adverse effect of this type of hazard, which helps the autonomous vehicle to navigate safely around such hazards. We find that our developed DNN-based autonomous vehicle driving system, including hazardous object detection and semantic segmentation, improves the navigational ability of an autonomous vehicle to avoid a potential hazard by 21% compared with the traditional DNN-based autonomous vehicle driving system.

scholarly journals Investigating the Potential of Network Optimization for a Constrained Object Detection Problem

2021 ◽  
Vol 7 (4) ◽  
pp. 64
Author(s):  
Tanguy Ophoff ◽  
Cédric Gullentops ◽  
Kristof Van Beeck ◽  
Toon Goedemé
Keyword(s):  
Computational Complexity ◽  
Object Detection ◽  
Network Optimization ◽  
Real Life ◽  
Optimization Techniques ◽  
Training Data ◽  
Single Shot ◽  
Standard Object ◽  
Number Of Classes

Object detection models are usually trained and evaluated on highly complicated, challenging academic datasets, which results in deep networks requiring lots of computations. However, a lot of operational use-cases consist of more constrained situations: they have a limited number of classes to be detected, less intra-class variance, less lighting and background variance, constrained or even fixed camera viewpoints, etc. In these cases, we hypothesize that smaller networks could be used without deteriorating the accuracy. However, there are multiple reasons why this does not happen in practice. Firstly, overparameterized networks tend to learn better, and secondly, transfer learning is usually used to reduce the necessary amount of training data. In this paper, we investigate how much we can reduce the computational complexity of a standard object detection network in such constrained object detection problems. As a case study, we focus on a well-known single-shot object detector, YoloV2, and combine three different techniques to reduce the computational complexity of the model without reducing its accuracy on our target dataset. To investigate the influence of the problem complexity, we compare two datasets: a prototypical academic (Pascal VOC) and a real-life operational (LWIR person detection) dataset. The three optimization steps we exploited are: swapping all the convolutions for depth-wise separable convolutions, perform pruning and use weight quantization. The results of our case study indeed substantiate our hypothesis that the more constrained a problem is, the more the network can be optimized. On the constrained operational dataset, combining these optimization techniques allowed us to reduce the computational complexity with a factor of 349, as compared to only a factor 9.8 on the academic dataset. When running a benchmark on an Nvidia Jetson AGX Xavier, our fastest model runs more than 15 times faster than the original YoloV2 model, whilst increasing the accuracy by 5% Average Precision (AP).

scholarly journals A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 517
Author(s):  
Seong-heum Kim ◽  
Youngbae Hwang
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Low Cost ◽  
Detection Methods ◽  
Future Research ◽  
3D Object ◽  
Practical Applications ◽  
Depth Sensors ◽  
Significant Research ◽  
3D Object Detection

Owing to recent advancements in deep learning methods and relevant databases, it is becoming increasingly easier to recognize 3D objects using only RGB images from single viewpoints. This study investigates the major breakthroughs and current progress in deep learning-based monocular 3D object detection. For relatively low-cost data acquisition systems without depth sensors or cameras at multiple viewpoints, we first consider existing databases with 2D RGB photos and their relevant attributes. Based on this simple sensor modality for practical applications, deep learning-based monocular 3D object detection methods that overcome significant research challenges are categorized and summarized. We present the key concepts and detailed descriptions of representative single-stage and multiple-stage detection solutions. In addition, we discuss the effectiveness of the detection models on their baseline benchmarks. Finally, we explore several directions for future research on monocular 3D object detection.

scholarly journals Autonomous Navigation of a Team of Unmanned Surface Vehicles for Intercepting Intruders on a Region Boundary

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 297
Author(s):  
Ali Marzoughi ◽  
Andrey V. Savkin
Keyword(s):  
Motion Control ◽  
Autonomous Vehicles ◽  
Autonomous Navigation ◽  
Control Algorithm ◽  
Autonomous Vehicle ◽  
Sufficient Conditions ◽  
Real Life ◽  
Unmanned Surface Vehicles ◽  
Necessary And Sufficient ◽  
See Region

We study problems of intercepting single and multiple invasive intruders on a boundary of a planar region by employing a team of autonomous unmanned surface vehicles. First, the problem of intercepting a single intruder has been studied and then the proposed strategy has been applied to intercepting multiple intruders on the region boundary. Based on the proposed decentralised motion control algorithm and decision making strategy, each autonomous vehicle intercepts any intruder, which tends to leave the region by detecting the most vulnerable point of the boundary. An efficient and simple mathematical rules based control algorithm for navigating the autonomous vehicles on the boundary of the see region is developed. The proposed algorithm is computationally simple and easily implementable in real life intruder interception applications. In this paper, we obtain necessary and sufficient conditions for the existence of a real-time solution to the considered problem of intruder interception. The effectiveness of the proposed method is confirmed by computer simulations with both single and multiple intruders.

Sign in / Sign up

Export Citation Format

Share Document