The Implementation of Objects Detection and Analysis Using Deep Learning with GPU

In the application of Artificial Intelligence (AI), image recognition is an important part. It is a combination of artificial intelligence and Machine Learning. Many jobs that require humans to spend time on processing can be more productive with the help of computers. For example, object detection can be applied to the police image system; the number of people on each occasion can be accurately calculated. Also, it can handle related cases in traffic control. In this paper, we propose the implementation of object detection and analysis using deep learning and GPU. First, we design the system architecture of object detection using Azure and GPU. Second, we deploy a system for identifying the presence of objects and identification the rectangular boundary surrounding each object.

[1]  Atsushi Ike,et al.  Speed-Up of Object Detection Neural Network with GPU , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[2]  Rubén D. Fonnegra,et al.  Performance comparison of deep learning frameworks in image classification problems using convolutional and recurrent networks , 2017, 2017 IEEE Colombian Conference on Communications and Computing (COLCOM).

[3]  Fatih Ertam,et al.  Data classification with deep learning using Tensorflow , 2017, 2017 International Conference on Computer Science and Engineering (UBMK).

[4]  Development of a deep learning neural network for human movements analysis , 2017, 2017 Second Russia and Pacific Conference on Computer Technology and Applications (RPC).

[5]  Zhiyi Qu,et al.  A convolutional neural network based on TensorFlow for face recognition , 2017, 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).

[6]  Marculet Dan-Georgian,et al.  GPU memory leveraged for accelerated training using Tensorflow , 2017 .

[7]  Martin Wattenberg,et al.  Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow , 2018, IEEE Transactions on Visualization and Computer Graphics.

[8]  Hitoshi Hayashi,et al.  Using Azure Machine Learning for Estimating Indoor Locations , 2017, 2017 International Conference on Platform Technology and Service (PlatCon).

[9]  Erdal Özbay,et al.  Image classification with caffe deep learning framework , 2017, 2017 International Conference on Computer Science and Engineering (UBMK).

[10]  Stefan Forsström,et al.  A performance and cost evaluation of combining OPC-UA and Microsoft Azure IoT Hub into an industrial Internet-of-Things system , 2017, 2017 Global Internet of Things Summit (GIoTS).

[11]  Richard Hill,et al.  Cloud-based scalable object detection and classification in video streams , 2018, Future Gener. Comput. Syst..