Vision Systems: Applications

Obinata G., Dutta A. (eds.) Vision systems. Applications (I-Tech, 2007)(ISBN 9783902613011)(616s)\_CsIp\_-o 4.1 Analysis of transmission and reconstruction rate for AMR perception Experimental data of image transmission rate and reconstruction rate is recorded using the 100 Mbps Ethernet and 11Mbps WLAN for mono-vision and stereovision cameras. The data is tabulated, analyzed, graphically illustrated and analyzed in this section. A. Image transmission and reconstruction using mono-vision camera: Using the approach discussed above, several processes are tabulated. First, colour images of resolution 768x576 are transmitted frame by frame from a mono-vision camera over 100 Mbps Ethernet and 11 Mbps WLAN and are reconstructed on the client side. The grab rate is around 13 fps, which is hardware dependent, comprising a mono-vision PULNIX-TMC6DSP camera with a Matrox Meteor-II/Standard frame grabber card. Next the image frame is serialized and is processed as a CSocket object. The image data is then written to the CListenSocket for transmission. Finally, there is an acknowledgement from the client side as per TCP/IP protocol, before the server is ready for sending the next frame. The process for image transmission is tabulated in Table 1 below: Approximate time in milliseconds Process Ethernet WLAN 1. Assembling an image frame for transmission 110 110 2. Acknowledgement from client 50 90-120 3. Total process time 160 200 - 230 Table 1. Time for transmitting a 768x576 JPEG image frame Next, the process on the client side is recorded. For fast, uninterrupted display, the image data is reconstructed using COM class, IPicture. The image data received by the client is loaded as a stream, using COM class IStream, in the memory as a CMemFile object using CArchive class. The breakup of the total process time for receiving the frame-by-frame image data on the client side through Ethernet and over WLAN is given in Table 2. Reading serialized data for reconstruction varies inversely with the throughput rate of the medium and there is no perceptible difference between transmitting image frames over these two media when it comes to viewing the environment through on-line reconstruction of the scene. Approximate time in milliseconds Process Ethernet WLAN 1. Reading serialized image data 280 280-380 2. Displaying an image frame 50 50 3. Total process time 330 330-430 Table 2. Time for displaying a 768x576 JPEG image frame The nature of image transmission over Ethernet and WLAN is graphically illustrated in Figure 12 and Figure 13. As the throughput rate of Ethernet is higher than that of WLAN, barring few aberrations, total process time for transmitting an image frame over Ethernet is around 160ms while transmitting the same frame over WLAN takes between 200 ms and 230 ms, as given in Table 1. Figure 13 shows that transmission over WLAN is more prone to environmental noise, common in a manufacturing environment. Unlike transmission over Ethernet where a steady rate is maintained, variable transmission rate over WLAN does not hamper the First of all, a short comparison of range sensors and their underlying principles was given. The chapter further focused on 3D cameras. The latest innovations have given a significant improvement for the measurement accuracy, wherefore this technology has attracted attention in the robotics community. This was also the motivation for the examination in this chapter. On this account, several applications were presented, which represents common problems in the domain of autonomous robotics. For the mapping example of static scenes, some difficulties have been shown. The low range, low apex angle and low dynamic range compared with 3D laser scanners, raised a lot of problems. Therefore, laser scanning is still the preferred technology for this use case. Based on the first experiences with the Swissranger SR-2 and the ICP based object localization, we will further develop the system and concentrate on the reliability and the robustness against inaccuracies in the initial pose estimation. Important for the reliability is knowledge about the accuracy of the determined pose. Indicators for this accuracy are, e.g., the number of matched points of the object data or the mean distance between found modelscene point correspondences. The feature tracking example highlights the potential for dynamic environments. Use cases with requirements of dynamic sensing are predestinated for 3D cameras. Whatever, these are the application areas 3D cameras were once developed. Our ongoing research in this field will concentrate on dynamic sensing in future. We are looking forward to new sensor innovations! Computer Vision is the most important key in developing autonomous navigation systems for interaction with the environment. It also leads us to marvel at the functioning of our own vision system. In this book we have collected the latest applications of vision research from around the world. It contains both the conventional research areas like mobile robot naviga- tion and map building, and more recent applications such as, micro vision, etc. The fist seven chapters contain the newer applications of vision like micro vision, grasping using vision, behavior based perception, inspection of railways and humanitarian demining. The later chapters deal with applications of vision in mobile robot navigation, camera cali- bration, object detection in vision search, map building, etc. We would like to thank all the authors for submitting the chapters and the anonymous re- viewers for their excellent work. Sincere thanks are also due to the editorial members of Advanced Robotic Systems publica- tions for all the help during the various stages of review, correspondence with authors and publication. We hope that you will enjoy reading this book and it will serve both as a reference and study material. Here, Applying A Fuzzy Model In Stereo Vision Of A 3p Robot Is Presented. According To The Simulation Results, Correlation Error Is Reduced Where The Best Result In A 3p Robot Applying Neural Networks Is About 97% Of Correctness, But Using A Fuzzy Approach, Let Us To Achieve Up To 100%. It Is Obvious That All These Results Are Achieved By Simulated Software And Different Kinds Of Errors Could Be Occurred In Real Environment. Some Of Them Are Discussed In(korayem Et Al., 2001).this Fuzzy Model Can Be Applied To A Large Class Of Robotic Manipulators.