Avaliação do Processo para Embarcar uma Rede Neural Baseada em YOLO Utilizando um Acelerador de Hardware Dedicado
Object Detection is a challenging task in computer vision, but Deep Neural Networks (DNN) have made great progress in this area. This work presents the process and the results obtained in the attempts to embed a YOLO V3 model in a Neural Compute Engine, the Movidius Stick. Experiments were carried out with a Tensorflow model that is converted to Movidius (using OpenVINO) including an evaluation of the Movidius stick connected to a Raspberry Pi3. The application uses aerial images of power distribution towers captured by a drone. Although there are some fully operational networks for Neural Compute Engines, there are some difficulties in porting new networks to the platform, with gains in performance, but with losses in accuracy.
B. Chen and X. Miao, “Distribution line pole detection and counting based on yolo using uav inspection line video,” Journal of Electrical Engineering & Technology, vol. 15, no. 1, pp. 441–448, 2020.
B. Moons, D. Bankman, and M. Verhelst, Embedded Deep Learning. Springer, 2019.
L. Liu, W. Ouyang, X. Wang, P. Fieguth, J. Chen, X. Liu, and M. Pietikainen, “Deep learning for generic object detection: A survey,” International journal of computer vision, vol. 128, no. 2, pp. 261–318,2020
J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
Y. Tian, G. Yang, Z. Wang, H. Wang, E. Li, and Z. Liang, “Apple detection during different growth stages in orchards using the improved yolo-v3 model,” Computers and electronics in agriculture, vol. 157, pp. 417–426, 2019.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788.
J. Redmon and A. Farhadi, “Yolo9000: Better, faster, stronger,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6517–6525.
“Intel® distribution of openvino™ toolkit — intel® software,” https://software.intel.com/en-us/openvino-toolkit, (Accessed on 12/20/2019).
A. Varghese, J. Gubbi, H. Sharma, and P. Balamuralidhar, “Power infrastructure monitoring and damage detection using drone captured images,” in 2017 International Joint Conference on Neural Networks(IJCNN). IEEE, 2017, pp. 1681–1687.
F. Guo, K. Hao, M. Xia, L. Zhao, L. Wang, and Q. Liu, “Detection of insulator defects based on yolo v3,” in International Conference on Artificial Intelligence for Communications and Networks. Springer, 2019, pp. 291–299
H. Chen, Z. He, B. Shi, and T. Zhong, “Research on recognition method of electrical components based on yolo v3,” IEEE Access, vol. 7, pp. 157 818–157 829, 2019.
Y. Xing, P. Kirkland, G. Di Caterina, J. Soraghan, and G. Matich, “Realtime embedded intelligence system: emotion recognition on raspberry pi with intel ncs,” in International Conference on Artificial Neural Networks. Springer, 2018, pp. 801–808.
A. Pester and M. Schrittesser, “Object detection with raspberry pi3 and movidius neural network stick,” in 2019 5th Experiment International Conference (exp. at’19). IEEE, 2019, pp. 326–330.
M. F. Ab Hamid and F. H. K. Zaman, “Hand gesture recognition using movidius neural compute stick,” in 2019 IEEE 9th International Conference on System Engineering and Technology (ICSET). IEEE, 2019, pp. 510–514.
N. Tiwari and K. Mondal, “Ncs based ultra low power optimized machine learning techniques for image classification,” in 2019 IEEE Region 10 Symposium (TENSYMP), 2019, pp. 750–753.
“Tensorflow,” https://www.tensorflow.org/, (Accessed on 08/07/2020).
“Opencv 4.0,” https://opencv.org/opencv-4-0/, (Accessed on 08/07/2020).
A. Pester and M. Schrittesser, “Object detection with raspberry pi3 and movidius neural network stick,” in 2019 5th Experiment International Conference (exp.at’19), 2019, pp. 326–330.