Name: Intelligent Robotic Visual Perception With Deep Learning
Price: 250 USD
Availability: InStock
ISBN: 9780443335327

Intelligent Robotic Visual Perception With Deep Learning, 1st Edition, examines deep learning technologies, algorithm analysis, and model construction for automated machine vision. Designed for engineers, researchers, and technical professionals across robotics, artificial intelligence, and computer vision, this volume outlines how algorithmic frameworks enable intelligent robot vision systems to interpret complex visual data.

The main coverage synthesizes fundamental recognition and tracking methodologies into structured technical arcs. The text analyzes visual object detection methods with specific focus on Region-based Fully Convolutional Networks (R-FCN) and Mask R-CNN architectures. It further examines multi-object tracking technologies by emphasizing sequence feature representations and context graph models.

Detailed case studies provide practical context by pairing algorithmic theory directly with real-world application scenarios. This structured approach supports technical specialists who construct functional visual perception architectures for robotic applications.

Chapter 1: An overview of the development and challenges of robot vision perception systems
Chapter 2: The components, main implementation steps, and typical applications of robot vision perception systems
Chapter 3: D deep learning technologies in robot vision perception systems
Chapter 4: Text detection based on image segmentation and sequence-based scene text recognition technologies in natural scenes
Chapter 5: Visual object detection technologies, with a focus on R-FCN-based and Mask RCNN-based object detection methods
Chapter 6: Multi-object tracking technologies, emphasizing sequence feature-based and context graph model-based multi-object tracking methods
Chapter 7: Image segmentation methods, with a focus on remote sensing image semantic segmentation using adaptive feature selection networks and region segmentation based on SU-SWA