A Deep Top-down Framework towards Generalisable Multi-View Pedestrian Detection

Engineering

• Multiple View 100%
• Ground Plane 100%
• Convolutional Neural Network 50%
• Multiple Camera 50%
• Homography 50%
• State-of-the-Art Method 50%
• Real World Application 50%
• Bottom-Up Approach 50%

Computer Science

• Generalization Performance 100%
• World Application 50%
• Convolutional Neural Network 50%
• Bottom-Up Approach 50%
• Training Dataset 50%

Chemical Engineering

• Neural Network 100%