Comparative Study of Different Classification Techniques for Pedestrian Detection Application
Main Article Content
Abstract
Pedestrian detection is well known as one of the most important applications in computer vision. However, reliable pedestrian detection is difficult due to a variety of factors, including changing size of pedestrian characteristics and crowded backgrounds. This study aims to evaluate and compare the pedestrian detection performance of three different types of classifiers: Random-Forest (RF), Convolution-Neural-Network (CNN), and Support-Vector-Machine (SVM). The presented methodology involves using You_Only_Look_Once (YOLOv8) architecture for object segmentation and the Histogram of Oriented Gradients (HOG) for feature extraction. Then, RF, CNN and SVM classifiers are trained and tested using the extracted HOG features. Using the EPFL pedestrian dataset, the experiment showed that the CNN model returned the highest results which had a speed of 0.42s and an accuracy percentage of 93.34%. Compared to SVM and RF, CNN provides a high detection speed and accuracy. RF has the slowest detection speed, while SVM has the lowest detection accuracy. This study gives useful information regarding the efficacy of these classifiers in detecting pedestrians under various weather circumstances, and the findings show that CNNs can achieve high accuracy while maintaining remarkable detection efficiency.
Article Details
How to Cite
Publication Dates
Received
Revised
Accepted
Published Online First
References
Aiad, B. A. E., Zarif, K. B., Gadallah, Z. M., and Abd EL-kareem, H., 2021. Support Vector Machine Kernel Functions Comparison. International Undergraduate Research Conference,5(5), pp. 84-88.
Aslan, M. F., Durdu, A., Sabanci, K., and Mutluer, M. A., 2020. CNN and HOG based comparison study for complete occlusion handling in human tracking. Measurement: Journal of the International Measurement Confederation, 158, P. 107704. https://doi.org/10.1016/j.measurement.2020.107704
Amraee, S., Chinipardaz, M. and Charoosaei, M., 2022. Analytical study of two feature extraction methods in comparison with deep learning methods for classification of small metal objects. Visual Computing for Industry, Biomedicine, and Art, 5(1), P.13. https://doi.org/10.1186/s42492-022-00111-6.
Alkentar, S. M., Alsahwa, B., Assalem, A., and Karakolla, D., 2021. Practical comparation of the accuracy and speed of YOLO, SSD and Faster RCNN for drone detection. Journal of Engineering, 27(8), pp. 19–31. https://doi.org/10.31026/j.eng.2021.08.02
Abdulmunem, M. E., and Hato, E., 2018. Outdoor Scene Classification Using Multiple SVM. Iraqi Journal of Science, pp. 2323-2335. https://doi.org/10.24996/ijs.2018.59.4C.20
Ali, M. A., Hussain, A. J., and Sadiq, A. T., 2022. Detection And Count of Human Bodies In a Crowd Scene Based on Enhancement Features By Using The YOLO v5 Algorithm. Iraqi Journal of Computers, Communications, Control and Systems Engineering, 22(2), pp.125-134. https://doi.org/10.33103/uot.ijccce.22.2.11
Braik, M., Al-Zoubi, H. and Al-Hiary, H., 2020. Pedestrian detection using multiple feature channels and contour cues with census transform histogram and random forest classifier. Pattern Analysis and Applications, 23(2), pp. 751–769. https://doi.org/10.1007/s10044-019-00835-x.
Byju, J., Chitra, R., Pranesh, P. E., Pavan, R. S., and Aravinth, J., 2021. Pedestrian Detection and Tracking in Challenging Conditions. In 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), Vol. 1, pp. 399-403. https://ieeexplore.ieee.org/document/9441934
Chong, P., and Tay, Y. H., 2017. A novel pedestrian detection and tracking with boosted HOG classifiers and Kalman filter. Proceedings - 14th IEEE Student Conference on Research and Development: Advancing Technology for Humanity, SCOReD 2016, pp.1-5. https://ieeexplore.ieee.org/document/7810052
Cortes, C., and Vapnik, V., 1995. Support-vector networks. Machine learning, 20, pp.273-297. https://doi.org/10.1007/BF00994018
Dalal, N., and Triggs, B., 2005. Histograms of oriented gradients for human detection. Proc 2005 IEEE Comput Soc Conf Comput Vis Pattern Recognit 1063-6919/05 $2000 © 2005 IEEE, 1, pp. 886–893. https://doi.org/10.1109/CVPR.2005.177
Diwakar and Raj, D., 2022. Recent Object Detection Techniques: A Survey. International Journal of Image, Graphics and Signal Processing, 14(2), pp. 47–60. https://doi.org/10.5815/ijigsp.2022.02.05
Dumitriu,A., Tatui,F., Miron,F., Ionescu,R.,Timofte,R., 2023. Rip Current Segmentation: A Novel Benchmark and YOLOv8 Baseline Results. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2023-June, pp. 1261–1271. https://doi.org/10.1109/CVPRW59228.2023.00133
Hiranmai, M., Krupa, N. B. and Nagaraj, H. K., 2018. Comparative Study of Various Feature Extraction Techniques for Pedestrian Detection. Procedia Computer Science, 154, pp. 622–628.
https://doi.org/10.1016/j.procs.2019.06.098
Haamied, R. D., Al-Abudi, B. Q. and Hassan, R. N., 2021. Automatic Object Detection, Labelling, and Localization by Cameras Drone System. Iraqi Journal of Science, 62(12), pp. 5008–5023. https://doi.org/10.24996/ijs.2021.62.12.37
Iftikhar, S., Zhang, Z., Asim, M., Muthanna, A., Koucheryavy, A., and Abd El-Latif, A. A., 2022. Deep Learning-Based Pedestrian Detection in Autonomous Vehicles: Substantial Issues and Challenges. Electronics, 11(21), P. 3551. https://doi.org/10.3390/electronics11213551
Joodi, M. A., Saleh, M. H., and Khadhim, D. J., 2023. Proposed Face Detection Classification Model Based on Amazon Web Services Cloud (AWS). Journal of Engineering, 29(4), pp. 176-206. https://doi.org/10.31026/j.eng.2023.04.12
Khalifa, A. B., Alouani, I., Mahjoub, M. A., and Amara, N. E. B., 2020. Pedestrian detection using a moving camera: A novel framework for foreground detection. Cognitive Systems Research, 60, pp. 77–96. https://doi.org/10.1016/j.cogsys.2019.12.003
Kang,J., Zhao,L.,Wang,K.,Shandong,K., 2023. Research on an Improved YOLOV8 Image Segmentation Model for Crop Pests. Advances in Computer, Signals and Systems,7(3), pp. 1–8. https://dx.doi.org/10.23977/acss.2023.070301.
Khan, Akib Mohi Ud Din Khanday, Q. R. and Rabani, S. T., 2021. Detecting Textual Propaganda Using Machine Learning Techniques. Baghdad Science Journal, 18, pp. 0199--0199. https://doi.org/10.21123/bsj.2020.17.1(Suppl.).0385.
Kim, B., Yuvaraj, N., Sri Preethaa, K. R., Santhosh, R., and Sabari, A., 2020. Enhanced pedestrian detection using optimized deep convolution neural network for smart building surveillance. Soft Computing, 24(22), pp. 17081-17092. https://doi.org/10.1007/s00500-020-04999-1
Lan, W., Dang, J., Wang, Y., and Wang, S., 2018, August. Pedestrian detection based on YOLO network model. In 2018 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 1547-1551. https://doi.org/10.1109/ICMA.2018.8484698.
Mateus, A., Ribeiro, D., Miraldo, P., and Nascimento, J. C., 2019. Efficient and robust Pedestrian Detection using Deep Learning for Human-Aware Navigation. Robotics and Autonomous Systems, 113, pp. 23–37. https://doi.org/10.1016/j.robot.2018.12.007.
Mohsin, A., and Sadoon, M., 2019. Developing an Arabic Handwritten Recognition System by Means of Artificial Neural Network. Journal of Engineering and Applied Sciences, 15(1), pp. 1–3.
Mahdi, G. J. M., 2020. A modified support vector machine classifiers using stochastic gradient descent with application to leukemia cancer type dataset. Baghdad Science Journal, 17(4), pp. 1255–1266. https://doi.org/10.21123/bsj.2020.17.4.1255
Patel, N., Dabhi, V. and Adhvaryu, R., 2023. Identify Road Potholes Using Image Semanticsegmentation. Journal of Data Acquisition and Processing, 38(2), pp. 2307–2315. https://doi.org/10.5281/zenodo.776921.
Raghavachari, C., Aparna, V., Chithira, S., and Balasubramanian, V., 2015. A comparative study of vision based human detection techniques in people counting applications. Procedia Computer Science, 58, pp. 461-469. https://doi.org/10.1016/j.procs.2015.08.064
Reddy, R. V. K. and Babu, U. R., 2018. A Review on Classification Techniques in Machine Learning. International Journal of Advance Research in Science and Engineering, 7(30), pp. 40–47.
Rahman, M. M., Nooruddin, S., Hasan, K. A., and Dey, N. K., 2021. HOG + CNN Net: Diagnosing COVID-19 and Pneumonia by Deep Neural Network from Chest X-Ray Images. SN Computer Science, 2(5), pp. 1–15. https://doi.org/10.1007/s42979-021-00762-x
Seemanthini, K. and Manjunath, S. S., 2018. Human Detection and Tracking using HOG for Action Recognition. Procedia Computer Science, 132(Iccids), pp. 1317–1326.
https://doi.org/10.1016/j.procs.2018.05.048
Sancho, C., 2014. Pedestrian Detection using a boosted cascade of Histogram of Oriented Gradients. MSc. thesis, Department of Electrical Engineering, Linköping University.
Wang, B., 2019. Research on Pedestrian Detection Algorithm Based on Image. Journal of Physics: Conference Series, 1345(6), p. 062023. https://doi.org/10.1088/1742-6596/1345/6/062023.
Zuo, X., Li, J., Huang, J., Yang, F., Qiu, T., and Jiang, Y., 2021. Pedestrian detection based on one-stage YOLO algorithm. Journal of Physics: Conference Series, 1871(1), p. 012131. https://doi.org/10.1088/1742-6596/1871/1/012131.
Zhang, Y., Xu, L., and Zhang, Y., 2022. Research on hierarchical pedestrian detection based on SVM classifier with improved kernel function. Measurement and Control (United Kingdom), 55(9–10), pp. 1088–1096. https://doi.org/10.1177/00202940221110164