A Stream System-on-Chip Architecture for High Speed Target Recognition Based on Biologic Vision
نویسندگان
چکیده
For target recognition based on biologic vision, an application-specific stream SOC: MASA-MI is described in this paper. MASA-MI consists of several heterogeneous cores, and a stream accelerator core is used to accelerate matching image which consumes the most time in target recognition. We implemented it on Altera EP2S60 FPGA. Result shows the 166MHz MASA-MI provides a peak performance of 585 fps. MASA-MI’s performance is an order of magnitude higher than those of today’s DSPs such as the Texas Instruments TMS320DM642 (600MHz). On the other hand, the cost is far less than special purpose processors.
منابع مشابه
Vision Chip Architecture for Simultaneous Output of Multi-Target Positions
In this paper, we describe new vision chip architecture, which enables simultaneous output of multi-target positions. This architecture selects targets that don’t overlap at each other in the direction of the column and extracts the target positions simultaneously. Thanks to this simultaneous output, the vision chip based on the architecture can obtain many target positions at high-speed. On th...
متن کاملIdentification of Houseplants Using Neuro-vision Based Multi-stage Classification System
In this paper, we present a machine vision system that was developed on the basis of neural networks to identify twelve houseplants. Image processing system was used to extract 41 features of color, texture and shape from the images taken from front and back of the leaves. The features were fed into the neural network system as the recognition criteria and inputs. Multilayer perceptron (MLP) ne...
متن کاملA Digital Vision Chip Specialized for High-Speed Target Tracking
This paper describes a new vision chip architecture for high-speed target tracking. The processing speed and the number of pixels are improved by hardware implementation of a special algorithm which utilizes a property of high-speed vision and introduction of bit-serial and cumulative summation circuits. As a result, 18 objects in a 128 128 image can be tracked in 1 ms. Based on the architectur...
متن کاملHigh-speed sensory–motor fusion for robotic grasping
In this paper a new high-speed vision device and its application to a grasp system is proposed, and we discuss a processing architecture for grasping based on visual and tactile feedback designed with real-time control in mind. First, we describe a high-speed vision chip that serves as a robotic eye that includes a general-purpose parallel processing array along with a photo-detector all on a s...
متن کاملCommunication-Aware Face Detection Using Noc Architecture
Face detection is an essential first step towards many advanced computer vision, biometrics recognition and multimedia applications, such as face tracking, face recognition, and video surveillance. In this paper, we proposed an FPGA hardware design with NoC (Network-on-Chip) architecture based on an AdaBoost face detection algorithm. The AdaBoost-based method is the state-of-the-art face detect...
متن کامل