Embedded Computer Vision

As a graduate student at Ohio State in the mid-1970s, I inherited a unique c- puter vision laboratory from the doctoral research of previous students. They had designed and built an early frame-grabber to deliver digitized color video from a (very large) electronic video camera on a tripod to a mini-computer (sic) with a (huge!) disk drive—about the size of four washing machines. They had also - signed a binary image array processor and programming language, complete with a user’s guide, to facilitate designing software for this one-of-a-kindprocessor. The overall system enabled programmable real-time image processing at video rate for many operations. I had the whole lab to myself. I designed software that detected an object in the eldofview,trackeditsmovementsinrealtime,anddisplayedarunningdescription of the events in English. For example: “An object has appeared in the upper right corner...Itismovingdownandtotheleft...Nowtheobjectisgettingcloser...The object moved out of sight to the left”—about like that. The algorithms were simple, relying on a suf cient image intensity difference to separate the object from the background (a plain wall). From computer vision papers I had read, I knew that vision in general imaging conditions is much more sophisticated. But it worked, it was great fun, and I was hooked.

As a graduate student at Ohio State in the mid-1970s, I inherited a unique c- puter vision laboratory from the doctoral research of previous students. They had designed and built an early frame-grabber to deliver digitized color video from a (very large) electronic video camera on a tripod to a mini-computer (sic) with a (huge!) disk drive—about the size of four washing machines. They had also - signed a binary image array processor and programming language, complete with a user’s guide, to facilitate designing software for this one-of-a-kindprocessor. The overall system enabled programmable real-time image processing at video rate for many operations. I had the whole lab to myself. I designed software that detected an object in the eldofview,trackeditsmovementsinrealtime,anddisplayedarunningdescription of the events in English. For example: “An object has appeared in the upper right corner...Itismovingdownandtotheleft...Nowtheobjectisgettingcloser...The object moved out of sight to the left”—about like that. The algorithms were simple, relying on a suf cient image intensity difference to separate the object from the background (a plain wall). From computer vision papers I had read, I knew that vision in general imaging conditions is much more sophisticated. But it worked, it was great fun, and I was hooked.

Hardware Considerations for Embedded Vision Systems.- Design Methodology for Embedded Computer Vision Systems.- We Canwatch It For You Wholesale.- Advances in Embedded Computer Vision.- Using Robust Local Features on DSP-Based Embedded Systems.- Benchmarks of Low-Level Vision Algorithms for DSP, FPGA, and Mobile PC Processors.- SAD-Based Stereo Matching Using FPGAs.- Motion History Histograms for Human Action Recognition.- Embedded Real-Time Surveillance Using Multimodal Mean Background Modeling.- Implementation Considerations for Automotive Vision Systems on a Fixed-Point DSP.- Towards OpenVL: Improving Real-Time Performance of Computer Vision Applications.- Looking Ahead.- Mobile Challenges for Embedded Computer Vision.- Challenges in Video Analytics.- Challenges of Embedded Computer Vision in Automotive Safety Systems.