Autonomous vehicles have become the recent trends, these vehicles require various functions to perform in parallel. One such function is target object detection and classification of the target object, which would aid the performance of the vehicle at various scenarios. Over the years various object detection and classification algorithms have been proposed. The paper gives overview of different kind of algorithms and methods used for object detection and classification. In Advance Diver Assistance System (ADAS), the Autonomous Emergency Braking System function depends upon the target vehicles on road in real time. So it is important to detect the object and classify them to improve the performance of the ADAS.
Published In:IJCSN Journal Volume 8, Issue 1
Date of Publication : February 2019
Pages : 24-27
Figures :01
Tables : 01
Hitesh Kumar Jain Jathanraj :
Department of Electronics and Communication Engineering, SRM Institute of Science and Technology,
Kanchipuram dist., Tamil Nadu 603 203, India.
ADAS, Deep Learning, CNN, Object Detection, Object Classification
This survey paper gives an overview of recent algorithms used for object detection and classifications. To improve the performance of the ADAS real-time detection of object algorithm needs to be robust in nature with high accuracy. Various algorithms with improved accuracy are available for object detection by using Deep Neural Network, Region based full Convolution Network, Darknet Architecture, semantic features extraction, Convolution Neural Network, Pointnet Architecture, etc. Among these Darknet based deep learning method implemented with the help of YOLO provides better object detection in real time application.
[1] Soin, Akhil, and Manisha Chahande. "Moving vehicle detection using deep neural network." In Emerging Trends in Computing and Communication Technologies (ICETCCT), International Conference, IEEE (2017), pp. 1-5. [2] Zhang, Zhaojin, Cunlu Xu, and Wei Feng. "Road vehicle detection and classification based on deep neural network." In Software Engineering and Service Science (ICSESS), 2016 7th IEEE International Conference, IEEE (2016), pp. 675-678. [3] Zhigang, Zhou, Lei Huan, Ding Pengcheng, Zhou Guangbing, Wang Nan, and Zhou Wei-Kun. "Vehicle target detection based on R-FCN." In 2018 Chinese Control and Decision Conference (CCDC), IEEE (2018), pp. 5739-5743. [4] Kim, Jinwoo, Yongbon Koo, and SungHoon Kim. "MOD: Multi-camera Based Local Position Estimation for Moving Objects Detection." In Big Data and Smart Computing (BigComp), 2018 IEEE International Conference, IEEE (2018) pp. 642-643. [5] Liu, Tianrui, and Tania Stathaki. "Enhanced pedestrian detection using deep learning based semantic image segmentation." In Digital Signal Processing (DSP), 2017 22nd International Conference, IEEE (2017), pp. 1-5. [6] Huo, Zhuoqun, Yizhang Xia, and Bailing Zhang. "Vehicle type classification and attribute prediction using multi-task RCNN." In Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), International Congress, IEEE (2016), pp. 564-569. [7] Dong, Zhen, Yuwei Wu, Mingtao Pei, and Yunde Jia. "Vehicle type classification using a semisupervised convolutional neural network." IEEE transactions on intelligent transportation systems 16, no. 4 (2015): 2247-2256.
