Road Object Detection using SSD-MobileNet Algorithm: Case Study for Real-Time ADAS Applications

Omar Bouazizi, Chaimae Azroumahli, Aimad El Mourabit, Mustapha Oussouaddi

Abstract


Object detection has played a crucial role in Advanced Driver Assistance Systems (ADAS) applications, particularly with integrating deep learning techniques. These advancements have improved ADAS applications by enabling more precise object identification, thereby enhancing real-time decision-making. Object detection models can be categorized into two main groups: two-stage and one-stage models. While prior studies reveal that one-stage detectors generally achieve higher frames per second (FPS) at the expense of some accuracy, they remain better suited for real-time ADAS applications. Our study aims to analyze the performance of an object detection model created using SSD-MobileNet, a one-stage detector approach. We focused on identifying road-related objects such as vehicles, and traffic signs. The contribution of our work lies in developing an object detection model using a pre-trained SSD-MobileNet and employing transfer learning. This process involves introducing a new fully connected layer tailored for the specific identification of objects in road scenes. The retraining of the SSD-MobileNet model is executed through GPU-accelerated transfer learning on the MS COCO dataset, incorporating appropriate pre-processing to exclusively include road-related objects. Our findings indicate promising results for the retrained SSD-MobileNet model, achieving an F1 score of 0.801, and a Mean Average Precision (mAP) of 65.41 at 71 FPS. A comparative analysis with other one-stage and two-stage detectors demonstrates the model's performance, surpassing some existing works in the literature related to road object detection. Notably, our model exhibits improved mAP while maintaining a higher FPS, rendering it more apt for ADAS applications.

Keywords


ADAS; SSD-MobileNet; CNN; Object Detection; Transfer Learning; FPS; MS COCO.

Full Text:

PDF

References


M. Iqbal, J. C. Han, Z. Q. Zhou, D. Towey, and T. Y. Chen, “Metamorphic testing of Advanced Driver-Assistance System (ADAS) simulation platforms: Lane Keeping Assist System (LKAS) case studies,” Inf. Softw. Technol., vol. 155, p. 107104, Mar. 2023, doi: 10.1016/J.INFSOF.2022.107104.

C. A. DeGuzman and B. Donmez, “Drivers don’t need to learn all ADAS limitations: A comparison of limitation-focused and responsibility-focused training approaches,” Accid. Anal. Prev., vol. 178, p. 106871, Dec. 2022, doi: 10.1016/J.AAP.2022.106871.

T.-M. Guerra, D. Berdjag, P. Polet, and T. A.-T. Nguyen, “Toward a Cooperative ADAS for Train Driving based on Real-Time Human Parameters and Delay Estimation,” IFAC-PapersOnLine, vol. 56, no. 2, pp. 3534–3539, Jan. 2023, doi: 10.1016/j.ifacol.2023.10.1510.

P. M. Greenwood, J. K. Lenneman, and C. L. Baldwin, “Advanced driver assistance systems (ADAS): Demographics, preferred sources of information, and accuracy of ADAS knowledge,” Transp. Res. Part F Traffic Psychol. Behav., vol. 86, pp. 131–150, Apr. 2022, doi: 10.1016/j.trf.2021.08.006.

F. Novakazi, J. Orlovska, L. O. Bligård, and C. Wickman, “Stepping over the threshold linking understanding and usage of Automated Driver Assistance Systems (ADAS),” Transp. Res. Interdiscip. Perspect., vol. 8, p. 100252, Nov. 2020, doi: 10.1016/J.TRIP.2020.100252.

I. Athanasiadis, P. Mousouliotis, and L. Petrou, “A Framework of Transfer Learning in Object Detection for Embedded Systems,” arXiv preprint arXiv:1811.04863, 2018.

I. M. Harms, L. Bingen, and J. Steffens, “Addressing the awareness gap: A combined survey and vehicle registration analysis to assess car owners’ usage of ADAS in fleets,” Transp. Res. Part A Policy Pract., vol. 134, pp. 65–77, Apr. 2020, doi: 10.1016/j.tra.2020.01.018.

J. Orlovska, F. Novakazi, B. Lars-Ola, M. A. Karlsson, C. Wickman, and R. Söderberg, “Effects of the driving context on the usage of Automated Driver Assistance Systems (ADAS) -Naturalistic Driving Study for ADAS evaluation,” Transp. Res. Interdiscip. Perspect., vol. 4, p. 100093, Mar. 2020, doi: 10.1016/J.TRIP.2020.100093.

A. Gupta, A. Anpalagan, L. Guan, and A. S. Khwaja, “Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues,” Array, vol. 10, p. 100057, Jul. 2021, doi: 10.1016/j.array.2021.100057.

N. Youssouf, “Traffic sign classification using CNN and detection using faster-RCNN and YOLOV4,” Heliyon, vol. 8, no. 12, p. e11792, Dec. 2022, doi: 10.1016/j.heliyon.2022.e11792.

L. Geng, J. Sun, Z. Xiao, F. Zhang, and J. Wu, “Combining CNN and MRF for road detection,” Computers and Electrical Engineering, vol. 70, pp. 895–903, Aug. 2018, doi: 10.1016/j.compeleceng.2017.11.026.

R. Girshick, “Fast R-CNN,” in Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448, 2015, doi: 10.1109/ICCV.2015.169.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 779–788, 2016, doi: 10.1109/CVPR.2016.91.

W. Liu et al., “SSD: Single shot multibox detector,” in Lecture Notes in Computer Science, vol. 9905, pp. 21–37, 2016, doi: 10.1007/978-3-319-46448-0_2.

J. Yue et al., “Hyperspectral-to-image transform and CNN transfer learning enhancing soybean LCC estimation,” Comput. Electron. Agric., vol. 211, Aug. 2023, doi: 10.1016/j.compag.2023.108011.

Y. Song, L. Gao, X. Li, and W. Shen, “A novel robotic grasp detection method based on region proposal networks,” Robot. Comput. Integr. Manuf., vol. 65, p. 101963, Oct. 2020, doi: 10.1016/j.rcim.2020.101963.

K. A. Vinodhini and K. R. A. Sidhaarth, “Pothole detection in the bituminous road using CNN with transfer learning,” Measurement: Sensors, p. 100940, Feb. 2023, doi: 10.1016/j.measen.2023.100940.

A. A. Shetty, N. T. Hegde, A. C. Vaz, and C. R. Srinivasan, “Multi Cost Function Fuzzy Stereo Matching Algorithm for Object Detection and Robot Motion Control,” Journal of Robotics and Control (JRC), vol. 4, no. 3, pp. 356–370, Jun. 2023, doi: 10.18196/jrc.v4i3.17041.

S. Wang, “Research towards Yolo-Series Algorithms: Comparison and Analysis of Object Detection Models for Real-Time UAV Applications,” in Journal of Physics: Conference Series, p. 012021, 2021, doi: 10.1088/1742-6596/1948/1/012021.

D. Biswas, H. Su, C. Wang, A. Stevanovic, and W. Wang, “An automatic traffic density estimation using Single Shot Detection (SSD)and MobileNet-SSD,” Physics and Chemistry of the Earth, vol. 110, pp. 176–184, Apr. 2019, doi: 10.1016/j.pce.2018.12.001.

I. Shafi, A. Mazahir, A. Fatima, and I. Ashraf, “Internal defects detection and classification in hollow cylindrical surfaces using single shot detection and MobileNet,” Measurement, vol. 202, p. 111836, Oct. 2022, doi: 10.1016/J.MEASUREMENT.2022.111836.

Y. Liu, Z. Wang, R. Wang, J. Chen, and H. Gao, “Flooding-based MobileNet to identify cucumber diseases from leaf images in natural scenes,” Comput. Electron. Agric., vol. 213, p. 108166, Oct. 2023, doi: 10.1016/j.compag.2023.108166.

Z. Chen et al., “Fast vehicle detection algorithm in traffic scene based on improved SSD,” Measurement, vol. 201, p. 111655, Sep. 2022, doi: 10.1016/j.measurement.2022.111655.

K. Tong and Y. Wu, “Rethinking PASCAL-VOC and MS-COCO dataset for small object detection,” J. Vis. Commun. Image Represent, vol. 93, p. 103830, May 2023, doi: 10.1016/j.jvcir.2023.103830.

S. Chun, W. Kim, S. Park, M. Chang, and S. J. Oh, “ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO,” in Lecture Notes in Computer Science, pp. 1–19, 2022, doi: 10.1007/978-3-031-20074-8_1.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, May 2017, doi: 10.1145/3065386.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2015.

A. Vaswani et al., “Attention Is All You Need,” Advances in neural information processing systems, vol. 30, 2017.

K. Zhang, W. Wang, Z. Lv, Y. Fan, and Y. Song, “Computer vision detection of foreign objects in coal processing using attention CNN,” Eng. Appl. Artif. Intell., vol. 102, p. 104242, Jun. 2021, doi: 10.1016/J.ENGAPPAI.2021.104242.

Y. Ji, H. Zhang, Z. Zhang, and M. Liu, “CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances,” Inf. Sci., vol. 546, pp. 835–857, Feb. 2021, doi: 10.1016/j.ins.2020.09.003.

Y. Shao, D. Zhang, H. Chu, X. Zhang, and Y. Rao, “A Review of YOLO Object Detection Based on Deep Learning,” Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, vol. 44, no. 10, pp. 3697–3708, 2022, doi: 10.11999/JEIT210790.

R. I. H. Abushahma, M. A. M. Ali, O. I. Al-Sanjary, and N. M. Tahir, “Region-based Convolutional Neural Network as Object Detection in Images,” in 2019 IEEE 7th Conference on Systems, Process and Control (ICSPC), pp. 264–268, 2019, doi: 10.1109/ICSPC47137.2019.9068011.

S. Nandyal and S. Sharanabasappa, “Deep ResNet 18 and enhanced firefly optimization algorithm for on-road vehicle driver drowsiness detection,” Journal of Autonomous Intelligence, vol. 7, no. 3, Jan. 2024, doi: 10.32629/jai.v7i3.975.

B. P. Kaur et al., “An augmentation aided concise CNN based architecture for COVID-19 diagnosis in real time,” Sci. Rep., vol. 14, no. 1, p. 1136, Jan. 2024, doi: 10.1038/s41598-024-51317-y.

M. T. Ahad, Y. Li, B. Song, and T. Bhuiyan, “Comparison of CNN-based deep learning architectures for rice diseases classification,” Artificial Intelligence in Agriculture, vol. 9, pp. 22–35, Sep. 2023, doi: 10.1016/j.aiia.2023.07.001.

N. D. Nguyen, T. Do, T. D. Ngo, and D. D. Le, “An Evaluation of Deep Learning Methods for Small Object Detection,” Journal of Electrical and Computer Engineering, vol. 2020, 2020, doi: 10.1155/2020/3189691.

T. Chen, N. Wang, R. Wang, H. Zhao, and G. Zhang, “One-stage CNN detector-based benthonic organisms detection with limited training dataset,” Neural Networks, vol. 144, pp. 247–259, Dec. 2021, doi: 10.1016/J.NEUNET.2021.08.014.

P. Song, P. Li, L. Dai, T. Wang, and Z. Chen, “Boosting R-CNN: Reweighting R-CNN samples by RPN’s error for underwater object detection,” Neurocomputing, vol. 530, pp. 150–164, Apr. 2023, doi: 10.1016/J.NEUCOM.2023.01.088.

Y. Huang, Y. Qian, H. Wei, Y. Lu, B. Ling, and Y. Qin, “A survey of deep learning-based object detection methods in crop counting,” Comput. Electron. Agric., vol. 215, p. 108425, Dec. 2023, doi: 10.1016/J.COMPAG.2023.108425.

F. M. T. R. Kinasih, C. Machbub, L. Yulianti, and A. S. Rohman, “Two-stage multiple object detection using CNN and correlative filter for accuracy improvement,” Heliyon, vol. 9, no. 1, p. e12716, Jan. 2023, doi: 10.1016/J.HELIYON.2022.E12716.

R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580-587, 2014.

F. Alamri and N. Pugeault, “Improving Object Detection Performance Using Scene Contextual Constraints,” IEEE Trans. Cogn. Dev. Syst., vol. 14, no. 4, pp. 1320–1330, Dec. 2022, doi: 10.1109/TCDS.2020.3008213.

M. Zabihi et al., “Leveraging Ellipsoid Bounding Shapes and Fast R-CNN for Enlarged Perivascular Spaces Detection and Segmentation,” International Workshop on Machine Learning in Medical Imaging, pp. 325-334, 2023.

V. K. Sharma and R. N. Mir, “A comprehensive and systematic look up into deep learning based object detection techniques: A review,” Computer Science Review, vol. 38, p. 100301, 2020, doi: 10.1016/j.cosrev.2020.100301.

A. Umamageswari, S. Deepa, A. Bhagyalakshmi, A. Sangari, and K. Raja, “EmotionFusion: A unified ensemble R-CNN approach for advanced facial emotion analysis,” Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 10141–10155, Dec. 2023, doi: 10.3233/JIFS-233842.

K. He, X. Zhang, S. Ren, and J. Sun, “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,” IEEE transactions on pattern analysis and machine intelligence, vol. 37, no. 9, pp. 1904-1916, 2014.

J. Chen, J. Chen, W. Wang, and Y. Zhu, “Improved model for image tampering monitoring based on fast-RCNN,” 2023 2nd International Conference on Data Analytics, Computing and Artificial Intelligence (ICDACAI), pp. 760–764, 2023, doi: 10.1109/ICDACAI59742.2023.00150.

S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Trans Pattern Anal Mach Intell, vol. 39, no. 6, pp. 1137–1149, 2017, doi: 10.1109/TPAMI.2016.2577031.

Y. Wu, “Research on embroidery image recognition based on deep learning,” in Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), p. 61, 2023, doi: 10.1117/12.3005861.

L. Wang, “Faster R-CNN-based pedestrian detection and tracking,” in Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), p. 154, 2023, doi: 10.1117/12.3006095.

K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” IEEE Trans Pattern Anal Mach Intell, vol. 42, no. 2, pp. 386–397, Mar. 2020, doi: 10.1109/TPAMI.2018.2844175.

X. Li, T. Lai, S. Wang, Q. Chen, C. Yang, and R. Chen, “Weighted feature pyramid networks for object detection,” in Proceedings - 2019 IEEE Intl Conf on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking, pp. 1500–1504, 2019, doi: 10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00217.

P. Chotikunnan, T. Puttasakul, R. Chotikunnan, B. Panomruttanarug, M. Sangworasil, and A. Srisiriwat, “Evaluation of Single and Dual Image Object Detection through Image Segmentation Using ResNet18 in Robotic Vision Applications,” Journal of Robotics and Control (JRC), vol. 4, no. 3, pp. 263–277, Apr. 2023, doi: 10.18196/jrc.v4i3.17932.

D. Reis, J. Kupec, J. Hong, and A. Daoudi, “Real-Time Flying Object Detection with YOLOv8,” arXiv preprint arXiv:2305.09972, 2023.

B. Li, D. Jiang, X. Tang, Y. Sun, and Y. Weng, “Mobilenetv2-SSD Target Detection Method Based on Multi-scale Feature Fusion,” International Conference on Cognitive Systems and Signal Processing, pp. 206-217, 2023.

R. Del Prete, M. D. Graziano, and A. Renga, “RetinaNet: A deep learning architecture to achieve a robust wake detector in SAR images,” in 6th International Forum on Research and Technology for Society and Industry, RTSI 2021, pp. 171–176, 2021, doi: 10.1109/RTSI50628.2021.9597297.

Y. Li, Y. Ma, and Y. Long, “Protocol for assessing neighborhood physical disorder using the YOLOv8 deep learning model,” STAR Protoc., vol. 5, no. 1, p. 102778, Mar. 2024, doi: 10.1016/j.xpro.2023.102778.

S. Bhumbla, D. K. Gupta, and Nisha, “A Review: Object Detection Algorithms,” in ICSCCC 2023 - 3rd International Conference on Secure Cyber Computing and Communications, pp. 827–832, 2023, doi: 10.1109/ICSCCC58608.2023.10176865.

D. Li, M. Wang, Y. Zhang, and C. Zhai, “Application of an improved VGG and RPN network in precision parts recognition,” Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9403–9419, Dec. 2023, doi: 10.3233/JIFS-231730.

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, “Focal Loss for Dense Object Detection,” IEEE Trans Pattern Anal Mach Intell, vol. 42, no. 2, pp. 318–327, Aug. 2017, doi: 10.1109/TPAMI.2018.2858826.

X. Wen, X. Yu, Y. Wang, C. Yang, and Y. Sun, “A Hybrid 3D–2D Feature Hierarchy CNN with Focal Loss for Hyperspectral Image Classification,” Remote Sens., vol. 15, no. 18, p. 4439, Sep. 2023, doi: 10.3390/rs15184439.

X. Lu, Q. Li, B. Li, and J. Yan, “MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection,” in Lecture Notes in Computer Science, pp. 541–557, 2020, doi: 10.1007/978-3-030-58568-6_32.

L. Du, R. Zhang, and X. Wang, “Overview of two-stage object detection algorithms,” in Journal of Physics: Conference Series, IOP Publishing, p. 012033, 2020, doi: 10.1088/1742-6596/1544/1/012033.

N. P. A. Duong, A. Almin, L. Lemarié, and B. R. Kiran, “Active Learning with Data Augmentation Under Small vs Large Dataset Regimes for Semantic-KITTI Dataset,” in Communications in Computer and Information Science, Springer Science and Business Media Deutschland GmbH, pp. 268–280, 2023, doi: 10.1007/978-3-031-45725-8_13.

S. Batool and J. Bang, “Classification of Short Circuit Marks in Electric Fire Case with Transfer Learning and Fine-Tuning the Convolutional Neural Network Models,” Journal of Electrical Engineering and Technology, vol. 18, no. 6, pp. 4329–4339, Nov. 2023, doi: 10.1007/s42835-023-01490-3.

H. Mzoughi, I. Njeh, M. Ben Slima, and A. BenHamida, “Deep efficient-nets with transfer learning assisted detection of COVID-19 using chest X-ray radiology imaging,” Multimed. Tools Appl., vol. 82, no. 25, pp. 39303–39325, Oct. 2023, doi: 10.1007/s11042-023-15097-3.

H. Wang, F. Lu, X. Tong, X. Gao, L. Wang, and Z. Liao, “A model for detecting safety hazards in key electrical sites based on hybrid attention mechanisms and lightweight Mobilenet,” Energy Reports, vol. 7, pp. 716–724, Nov. 2021, doi: 10.1016/j.egyr.2021.09.200.

M. R. Shoaib, M. R. Elshamy, T. E. Taha, A. S. El-Fishawy, and F. E. Abd El-Samie, “Efficient Brain Tumor Detection Based on Deep Learning Models,” in Journal of Physics: Conference Series, vol. 2128, no. 1, p. 012012, 2021.

L. Jing and Y. Tian, “Self-Supervised Visual Feature Learning with Deep Neural Networks: A Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 11. pp. 4037–4058, Feb. 16, 2021. doi: 10.1109/TPAMI.2020.2992393.

S. A. Sanchez, H. J. Romero, and A. D. Morales, “A review: Comparison of performance metrics of pretrained models for object detection using the TensorFlow framework,” in IOP Conference Series: Materials Science and Engineering, 2020, doi: 10.1088/1757-899X/844/1/012024.

S. S. A. Zaidi, M. S. Ansari, A. Aslam, N. Kanwal, M. Asghar, and B. Lee, “A survey of modern deep learning based object detection models,” Digital Signal Processing: A Review Journal, vol. 126, 2022, doi: 10.1016/j.dsp.2022.103514.

K. Su, L. Cao, B. Zhao, N. Li, D. Wu, and X. Han, “N-IoU: better IoU-based bounding box regression loss for object detection,” Neural Computing and Applications, vol. 36, no. 6, pp. 3049-3063 2023.

J. Yin, J. Qu, W. Huang, and Q. Chen, “Road damage detection and classification based on multi-level feature pyramids,” KSII Transactions on Internet and Information Systems, vol. 15, no. 2, pp. 786–799, Feb. 2021, doi: 10.3837/tiis.2021.02.022.




DOI: https://doi.org/10.18196/jrc.v5i2.21145

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Omar Bouazizi, Chaimae Azroumahli, Aimad El Mourabit, Mustapha Oussouaddi

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

 

Journal of Robotics and Control (JRC)

P-ISSN: 2715-5056 || E-ISSN: 2715-5072
Organized by Peneliti Teknologi Teknik Indonesia
Published by Universitas Muhammadiyah Yogyakarta in collaboration with Peneliti Teknologi Teknik Indonesia, Indonesia and the Department of Electrical Engineering
Website: http://journal.umy.ac.id/index.php/jrc
Email: jrcofumy@gmail.com

Kuliah Teknik Elektro Terbaik