Study of object detection using region-based fully convolutional neural networks
With the fast pace of economic development, deep learning has become one of the fastest growing field in recent over ten years. It has been applied and implemented widely such as Intelligent Transportation System (ITS), industrial automation system, data statistic and robotic. Convolutional Neural N...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| التنسيق: | Final Year Project |
| اللغة: | English |
| منشور في: |
2019
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | http://hdl.handle.net/10356/77769 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| الملخص: | With the fast pace of economic development, deep learning has become one of the fastest growing field in recent over ten years. It has been applied and implemented widely such as Intelligent Transportation System (ITS), industrial automation system, data statistic and robotic. Convolutional Neural Network (CNN) is one of the most representative network structures in deep learning technology, and has achieved great success in the field of image processing. This paper covers the concept and development of one of the most popular object detection method-region based fully convolutional neural network (R-FCN). And use high-end computer to evaluate the performance of the model in different data set training and compare with the other convolutional neural network method. |
|---|