Artificial vision system

Although technically and economically feasible artificial vision systems have been developed for the food industry, based on classic RGB video cameras, the... 

When technically - and economically - feasible, appropriate artificial vision systems have been developed for the food industry based on classical RGB video cameras. However, far too often, RGB vision systems fail to detect defects or contaminants. There are two main reasons for this poor performance. 

The hardware of the artificial vision system consists of an analog camera, a digitizer card, and a computer to process all the images captured from workspace. From the images, the information about the actual position of the mobile robot and the obstacles are obtained. The trajectory defined by the path planning method must be recalculated depending, for instance, on whether the mobile obstacle stops its execution. In the workspace, the stationary objects were identified with a blue color and the mobile obstacles with yellow. 

The control strategies include two different approaches divided as high-level control and low-level control (Tibaduiza, 2006). In the first, the free-obstacle path is calculated based on information from the artificial vision system and this is sent to the robot using RF communication (Figure 16). 

Figure 18 show an example of the results in the artificial vision system using two static and one mobile obstacle. This figure also shows how the elements in the workspace are correctly detected and are an example of the inputs in the path planning algorithms. 

More details and results of the artificial vision system can be found in Tibaduiza (2007). 

The points noted in this section are necessarily of a very limited range of vision. Most probably the real biological membrane is of much more complex nature than the artificial model systems. Yet the approaches sketched here may also have initiated the application of electrochemical methods to more practical cases [115]. 

More futuristic uses of chemical sensors and biosensors for processing could include artificial vision. For example, specific molecular vision complexes, such as the rhodopsin-opsin complex, have been isolated from ocular tissue and could be reconstructed into artificial membrane systems. Integration of such vision complexes with electronic U ansducers could result in artificial visioning sensors responding to specific wavelengths of light. Arrays of such sensors could result... 

Due to the complex structure of odor space, it is an extremely interesting and challenging question whether the olfactory system has a correlate of retinotopic maps in vision or frequency maps in audition. And if it does, what would be the organizing principle of such an odor map Furthermore, can we learn from this organization of biological olfactory systems to build artificial chemosensor systems that perform at levels comparable to the performance of the former in general olfactory sensing tasks ... 

Moving from advancements in current approaches to sensing and detections, one vision for 2030 is the use of an artificial immune system as a detector. Immune... 

Auzuir R. Alexandria was bom in Fortaleza, Brazil, in 1970. He is currently an Associate Professor with the Department of Automation and Control Engineering, Federal Institute for Education, Science, and Technology of Ceara (IFCE), Fortaleza, Brazil. He received the Ph D. degree from the Federal University of Ceara (UFC), Fortaleza, Brazil, in 2011. His research interests include embedded systems, industrial automation, artificial vision, and robotics. 

---