Evaluation of Image Detection Techniques Acquired from Camera Images

Year 2025, Volume: 9 Issue: 2, 33 - 43, 29.06.2025

Buğra Erkartal , Atınç Yılmaz

Abstract

In terms of situational awareness, object recognition, and real-time decision-making, abstract camera-based image detection methods have grown to be a core element of autonomous driving systems. This study presents a comprehensive evaluation of camera-based object detection techniques used in autonomous driving systems. Traditional methods such as Haar Cascades and HOG are reviewed alongside modern deep learning architectures including CNN, YOLO, and GANs. The study examines their strengths, weaknesses, and real-time performance across various detection tasks such as 2D/3D object detection, semantic/instance segmentation, and behavioral prediction. Especially promising for improving perceptual dependability under demanding environmental conditions and sensor fusion techniques combining data from lidar, radar, and cameras. By forecasting pedestrian and vehicle movements, deep learning-based behavioral prediction systems also greatly help to enable safer and more proactive driving. The results show that application-specific needs including accuracy, computational efficiency, and real-time processing should direct the choice of the suitable object identification technique. The findings suggest that no single technique is sufficient on its own; rather, the fusion of multiple systems, supported by adaptive and resource-efficient architectures, is crucial for safe and reliable autonomous driving. The research highlights the need for modular and scalable perception solutions capable of adapting to real-world complexities. Future studies should concentrate on the creation of low-cost, adaptive, multi-modal perception systems, which are fundamental for the safe and broad implementation of autonomous driving technology.

Keywords

Autonomous Driving , Segmentation , Deep Learning , Object Detection

References

• [1] P. Soviany and R. Tudor Ionescu, “Frustratingly easy trade-off optimization between single-stage and two-stage deep object detectors,” in Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, p. 0.
• [2] M. Carranza-Garcia, J. Torres-Mateo, P. Lara-Benitez, and J. Garcia-Gutiérrez, “On the performance of one-stage and two-stage object detectors in autonomous vehicles using camera data,” Remote Sens., vol. 13, no. 1, p. 89, 2020.
• [3] H. Liu, C. Wu, and H. Wang, “Real time object detection using LiDAR and camera fusion for autonomous driving,” Sci. Rep., vol. 13, no. 1, p. 8056, 2023.
• [4] J. Cao, H. Cholakkal, R. M. Anwer, F. S. Khan, Y. Pang, and L. Shao, “D2det: Towards high quality object detection and instance segmentation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11485–11494.
• [5] C. Zhang and C. Berger, “Pedestrian behavior prediction using deep learning methods for urban scenarios: A review,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 10, pp. 10279–10301, 2023.
• [6] S. Mohapatra, S. Yogamani, V. R. Kumar, S. Milz, H. Gotzig, and P. Mäder, “Lidar-bevmtn: Real-time lidar bird’s-eye view multi-task perception network for autonomous driving,” IEEE Trans. Intell. Transp. Syst., 2025.
• [7] L.-H. Wen and K.-H. Jo, “Fast and accurate 3D object detection for lidar-camera-based autonomous vehicles using one shared voxel-based backbone,” IEEE access, vol. 9, pp. 22080–22089, 2021.
• [8] N. Garnett et al., “Real-time category-based and general obstacle detection for autonomous driving,” in Proceedings of the IEEE International Conference on computer vision workshops, 2017, pp. 198–205.
• [9] H. Rashed, M. Ramzy, V. Vaquero, A. El Sallab, G. Sistu, and S. Yogamani, “Fusemodnet: Real-time camera and lidar based moving object detection for robust low-light autonomous driving,” in Proceedings of the IEEE/CVF international conference on computer vision workshops, 2019, p. 0.
• [10] D. Feng et al., “Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 3, pp. 1341–1360, 2020.
• [11] X. Yang, S. Wang, Y. Zhu, D. Zhou, and T. Li, “Context CVGN: A conditional multimodal trajectory prediction network based on scene semantic modeling,” Inf. Sci. (Ny)., vol. 666, p. 120433, 2024.
• [12] X. Shi, Y. D. Wong, C. Chai, and M. Z.-F. Li, “An automated machine learning (AutoML) method of risk prediction for decision-making of autonomous vehicles,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 11, pp. 7145–7154, 2020.
• [13] Y. Li, A. Fang, Y. Guo, and X. Wang, “Image Fusion Via Mutual Information Maximization for Semantic Segmentation in Autonomous Vehicles,” IEEE Trans. Ind. Informatics, vol. 20, no. 4, pp. 5838–5848, 2023.
• [14] B. De Brabandere, D. Neven, and L. Van Gool, “Semantic instance segmentation for autonomous driving,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp. 7–9.
• [15] J. Ren, S. D. Lee, X. Chen, B. Kao, R. Cheng, and D. Cheung, “Naive bayes classification of uncertain data,” in 2009 Ninth IEEE International Conference on Data Mining, 2009, pp. 944–949.
• [16] M. Ren and R. S. Zemel, “End-to-end instance segmentation with recurrent attention,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 6656–6664.
• [17] R. Marcuzzi, L. Nunes, L. Wiesmann, J. Behley, and C. Stachniss, “Mask-based panoptic lidar segmentation for autonomous driving,” IEEE Robot. Autom. Lett., vol. 8, no. 2, pp. 1141–1148, 2023.
• [18] C. Yin, J. Tang, T. Yuan, Z. Xu, and Y. Wang, “Bridging the gap between semantic segmentation and instance segmentation,” IEEE Trans. Multimed., vol. 24, pp. 4183–4196, 2021.
• [19] K. Goel, P. Srinivasan, S. Tariq, and J. Philbin, “Quadronet: Multi-task learning for real-time semantic depth aware instance segmentation,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 315–324.
• [20] S. Yao et al., “Radar-camera fusion for object detection and semantic segmentation in autonomous driving: A comprehensive review,” IEEE Trans. Intell. Veh., vol. 9, no. 1, pp. 2094–2128, 2023.
• [21] X. Dong, B. Zhuang, Y. Mao, and L. Liu, “Radar camera fusion via representation learning in autonomous driving,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 1672–1681.
• [22] C. Zhang, S. Lindner, I. M. Antolović, J. M. Pavia, M. Wolf, and E. Charbon, “A 30-frames/s, 252x144 SPAD Flash LiDAR With 1728 Dual-Clock 48.8-ps TDCs, and Pixel-Wise Integrated Histogramming,” IEEE J. Solid-State Circuits, vol. 54, no. 4, pp. 1137–1151, 2018.
• [23] H. A. Ignatious, H. El-Sayed, and P. Kulkarni, “Multilevel data and decision fusion using heterogeneous sensory data for autonomous vehicles,” Remote Sens., vol. 15, no. 9, p. 2256, 2023.
• [24] H. Razali, T. Mordan, and A. Alahi, “Pedestrian intention prediction: A convolutional bottom-up multi-task approach,” Transp. Res. part C Emerg. Technol., vol. 130, p. 103259, 2021.
• [25] M. Chaabane, A. Trabelsi, N. Blanchard, and R. Beveridge, “Looking ahead: Anticipating pedestrians crossing with future frames prediction,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2020, pp. 2297–2306.
• [26] Z. Yang, R. Zhang, G. Pandey, N. Masoud, and H. X. Liu, “A hierarchical vehicle behavior prediction framework with traffic signals and interactive agents,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 10, pp. 11066–11079, 2023.
• [27] S. Neogi, M. Hoy, K. Dang, H. Yu, and J. Dauwels, “Context model for pedestrian intention prediction using factored latent-dynamic conditional random fields,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 11, pp. 6821–6832, 2020.
• [28] L. Knoedler, C. Salmi, H. Zhu, B. Brito, and J. Alonso-Mora, “Improving pedestrian prediction models with self-supervised continual learning,” IEEE Robot. Autom. Lett., vol. 7, no. 2, pp. 4781–4788, 2022.
• [29] F. A. Barrios, A. Biswas, and A. Emadi, “Deep Learning-based Motion Prediction Leveraging Autonomous Driving Datasets: State-of-the-Art,” IEEE Access, 2024.
• [30] S. Rezaei, J. Gbadegoye, N. Masoud, and A. Khojandi, “A deep learning-based approach for vehicle motion prediction in autonomous driving,” in 2023 International Conference on Control, Automation and Diagnosis (ICCAD), 2023, pp. 1–6.
• [31] F. Wirthmüller, J. Schlechtriemen, J. Hipp, and M. Reichert, “Teaching vehicles to anticipate: A systematic study on probabilistic behavior prediction using large data sets,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 11, pp. 7129–7144, 2020.
• [32] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, 2001, vol. 1, pp. I--I.
• [33] M. A. Berwo et al., “Deep learning techniques for vehicle detection and classification from images/videos: A survey,” Sensors, vol. 23, no. 10, p. 4832, 2023.
• [34] Y. Hasan, M. U. Arif, A. Asif, and R. H. Raza, “Comparative analysis of vehicle detection in urban traffic environment using Haar cascaded classifiers and blob statistics,” in 2016 Future Technologies Conference (FTC), 2016, pp. 547–552.
• [35] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), 2005, vol. 1, pp. 886–893.
• [36] L. Cai, J. Zhu, H. Zeng, J. Chen, C. Cai, and K.-K. Ma, “HOG-assisted deep feature learning for pedestrian gender recognition,” J. Franklin Inst., vol. 355, no. 4, pp. 1991–2008, 2018.
• [37] J. Zhang, M. Huang, X. Jin, and X. Li, “A real-time Chinese traffic sign detection algorithm based on modified YOLOv2,” Algorithms, vol. 10, no. 4, p. 127, 2017.
• [38] Z. Wang, J. Chen, and S. C. H. Hoi, “Deep Learning for Image Super-Resolution: A Survey,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 10, pp. 3365–3387, 2021.
• [39] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
• [40] Y. Zhang, H. Xu, L. Huang, and C. Chen, “A storage-efficient SNN--CNN hybrid network with RRAM-implemented weights for traffic signs recognition,” Eng. Appl. Artif. Intell., vol. 123, p. 106232, 2023.
• [41] Z. Cai and N. Vasconcelos, “A real-time cascade pedestrian detection based on heterogeneous features,” in 2015 International SoC Design Conference (ISOCC), 2015, pp. 187–188.
• [42] Z. Jiang, L. Zhao, S. Li, and Y. Jia, “Real-time object detection method based on improved YOLOv4-tiny,” arXiv Prepr. arXiv2011.04244, 2020.
• [43] C. S. Asha and A. V Narasimhadhan, “Vehicle counting for traffic management system using YOLO and correlation filter,” in 2018 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), 2018, pp. 1–6.
• [44] H. Zhang et al., “Real-time detection method for small traffic signs based on Yolov3,” Ieee Access, vol. 8, pp. 64145–64156, 2020.
• [45] P. Mahto, P. Garg, P. Seth, and J. Panda, “Refining Yolov4 for vehicle detection,” Int. J. Adv. Res. Eng. Technol., vol. 11, no. 5, 2020.
• [46] M. Sahal, Z. Hidayat, Y. Bilfaqih, M. A. Hady, and Y. M. H. Tampubolon, “Smart Traffic Light Using YOLO Based Camera with Deep Reinforcement Learning Algorithm,” JAREE (Journal Adv. Res. Electr. Eng., vol. 7, no. 1, 2023.
• [47] K. Zhang, X. Feng, N. Jia, L. Zhao, and Z. He, “TSR-GAN: Generative adversarial networks for traffic state reconstruction with time space diagrams,” Phys. A Stat. Mech. its Appl., vol. 591, p. 126788, 2022.
• [48] Y. Zhang, S. Wang, B. Chen, J. Cao, and Z. Huang, “Trafficgan: Network-scale deep traffic prediction with generative adversarial nets,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 1, pp. 219–230, 2019.
• [49] F. Zhou, X. Xu, G. Trajcevski, and K. Zhang, “A survey of information cascade analysis: Models, predictions, and recent advances,” ACM Comput. Surv., vol. 54, no. 2, pp. 1–36, 2021.
• [50] R. Ahuja, A. Chug, S. Kohli, S. Gupta, and P. Ahuja, “The impact of features extraction on the sentiment analysis,” Procedia Comput. Sci., vol. 152, pp. 341–348, 2019.
• [51] A. R. Srinivasan et al., “Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 7, pp. 7166–7177, 2023.
• [52] L. G. Galvão and M. N. Huda, “Pedestrian and vehicle behaviour prediction in autonomous vehicle system—A review,” Expert Syst. Appl., vol. 238, p. 121983, 2024.
• [53] M. S. Salek, A. Al Mamun, and M. Chowdhury, “AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehicles,” arXiv Prepr. arXiv2401.14232, 2023.