ACRONYMS * ACC = Adaptive Cruise Control :AUTO: * AEB = Autonomous Emergency Breaking :AUTO: * AMF = Android Multimedia Framework (can be used on Linux too) Infrastructure for passing messages between a host and other cores (denoted as CEVA-Link in MM3K presentations) * BSD = Blind Spot Detection :AUTO: * FCW = Forward Collision Warning :AUTO: * ADAS = Advanced Driver Assistance Systems :AUTO: * ADK = Application Deveopment Kit (MM3K) * DVS = Digital Video Stabilizer * SR = Super-resolution * LDW = Lane Departure Warning :AUTO: * TSR = Traffic Sign Recognition :AUTO: * VDMA = Vector DMA (in CEVA-MM3K arch diagrams): access both ISDM and IVDM * VP = Vector Processor (in CEVA arch diagrams, IE the DSP core) * VPU = Vector Processor Unit in MM3K (in CEVA arch diagrams, cmp to VCU in XC*) * VLSU = Vector Processor Unit in MM3K (in CEVA arch diagrams) * VMEM = Vector MEMory (as opposed to SMEM) * SMEM = Sequancial? MEMory (as opposed to VMEM) * CISA = Configurable Instruction Set Architecture (& VGEN) * ISDM = Internal Sequential Data Memory (MM3K) * IVDM = Internal Vector Data Memory (MM3K) * MCMI = Multi Core Messaging Interface (MM3K) * ISP = Image Signal Processing (MM3K/CV applications) * CV = Computer Visiong * PC = Point Cloud A point cloud is a set of data points in some coordinate system. In a three-dimensional coordinate system, these points are usually defined by X, Y, and Z coordinates, and often are intended to represent the external surface of an object. Point clouds may be created by 3D scanners. These devices measure in an automatic way a large number of points on the surface of an object, and often output a point cloud as a data file. The point cloud represents the set of points that the device has measured. http://en.wikipedia.org/wiki/Point_cloud * PCL = Point Cloud Library (open source) http://en.wikipedia.org/wiki/Point_Cloud_Library * OOB = Out Of Box, usually referring to C source code without tweaks for target DSP. * LUT = Look-Up Table (a key-value kind of data structure) * SVM = * HDR = * TAM = * HOG : feature extraction for gesture recognition & palm tracking :CV: * Hough : The Hough transform is a feature extraction technique used :CV: in image analysis, computer vision, and digital image processing. http://en.wikipedia.org/wiki/Hough_transform * HAAR Like : :CV: * Harris Corner : :CV: * Kalman filter : A Kalman filter is an optimal estimator - :CV: ie infers parameters of interest from indirect, inaccurate and uncertain observations. It is recursive so that new measurements can be processed as they arrive. * Lucas-Kanade : optical flow :CV: * CNN : :CV: * Sobel : :CV: * KLT : optical flow for emotion detection :CV: * Block Matching : optical flow for emotion detection :CV: * MSER : feature extraction for gesture recognition & palm tracking :CV: * ORB : object detection & tracking :CV: * Fast9 : feature extraction for gesture recognition & palm tracking :CV: * SURF : feature extraction for gesture recognition & palm tracking :CV: * LBP : object detection & tracking :CV: * HAAR cascade : object detection & tracking :CV: * integral sum : object detection & tracking :CV: * matrix inversion/multiplication :CV: image operation for face detection & recognition * histogram : image operation for face detection & recognition :CV: * bilinear filter : for augmented reality :CV: * bicubic filter : for augmented reality :CV: * bilateral filter : for augmented reality :CV: * RANSAC : :CV: * FAST : :CV: * GoodFeaturesToTrack : :CV: * Addaboost : :CV: * Point Cloud Processing : :CV: * SAD = Sum of Absolute Differences : :CV: * OpenCV :CV: Open Computer Vision library, http://opencv.org/ documentation http://docs.opencv.org/trunk/index.html and here http://opencv.org/documentation.html 32- or 64-bit floating point based. "standard" under Khronos. ** GoodFeaturesToTrack part of OpenCV * CEVA-CV CEVA's OpenCV implementation on MM3k :CV: 16-bit fixed point vector based (VEC-C). * MISC ** NHTSA National Highway Traffic Safety Administration (US) ** NCAP New Car Assessment Program (US, run by NHTSA) ** Euro NCAP (backed by EU) ** IIHS Insurance Institute for Highway Safety (US) ** jello effect - caused by rooling shutter? ** rolling shutter effect *** what is it? http://www.youtube.com/watch?v=uFFRGSCmTWc *** what does it look like? http://www.youtube.com/watch?v=EaB9EHeDLSk * CEVA PARTNERS ** CVS : 3D stereo depth map ** nVisio : emotion detection ** "60 Mpps for 1080p30" IE 60 Megapixel/sec for 1080p 30 frames/sec * Autosar (AUTomotive Open System ARchitecture) :AUTO: http://www.autosar.org is a worldwide development partnership of car manufacturers, suppliers and other companies from the electronics, semiconductor and software industry. With the goals of: - Standardization of basic software functionality of automotive ECUs - Scalability to different vehicle and platform variants - Transferability of software - Support of different functional domains - Definition of an open architecture - Collaboration between various partners - Development of highly dependable systems - Sustainable utilization of natural resources - Support of applicable automotive international standards and state-of-the-art technologies * Khronos The Khronos Group - "Connecting Software to Silicon" The Khronos Group is a not for profit industry consortium creating open standards for the authoring and acceleration of parallel computing, graphics, dynamic media, computer vision and sensor processing on a wide variety of platforms and devices. All Khronos members are able to contribute to the development of Khronos API specifications, are empowered to vote at various stages before public deployment, and are able to accelerate the delivery of their cutting-edge 3D platforms and applications through early access to specification drafts and conformance tests. https://www.khronos.org/ ** OpenCL = a programming language (CEVA don't support) * SAFETY ** ISO 26262 :AUTO: ** ASIL-B :AUTO: there are 4 levels -A, -B, -C and -D (lower to higher) Automotive Safety Integrity Level (ASIL) is a risk classification scheme defined by the ISO 26262 - Functional Safety for Road Vehicles standard. This is an adaptation of the Safety Integrity Level used in IEC 61508 for the automotive industry. This classification helps defining the safety requirements necessary to be in line with the ISO 26262 standard. The ASIL is established by performing a risk analysis of a potential hazard by looking at the Severity, Exposure and Controllability of the vehicle operating scenario. The safety goal for that hazard in turn carries the ASIL requirements. http://en.wikipedia.org/wiki/Automotive_Safety_Integrity_Level :AUTO: * Zigbee, wireless communication protocoll * 6lowpan, wireless communication protocoll ? * IoT, Internet-of-Things * Whitespace protocol :COMMS: http://en.wikipedia.org/wiki/Weightless_(wireless_communications)