Intelligent Vision Processor

Overview

The Ceva-XM4 imaging and computer vision processor IP solves the most critical issues for the development of energy-efficient embedded vision systems where die size and power budget are extremely constrained, yet algorithms require intensive processing.

The Ceva-XM4 and the associated tools and libraries combine to deliver a comprehensive vision IP platform that allows developers to simply and easily address the three key elements of intelligent vision processing, namely 3D vision, computational photography and visual perception and analytics.

Choosing the Ceva-XM4 opens up a new world of possibilities for the designer including running computer vision on video streams (1080p, 4K); combining depth generation with vision processing; enabling multi-app processing (e.g. gesture + face detection + emotions + eye-tracking + depth); and implementing multi-image algorithms in high-resolution.

Fully programmable in high-level languages, the Ceva-XM4 is an extremely high-performance, low-power, fully synthesizable DSP and memory subsystem IP core incorporating a wide-vector architecture with fixed- and floating-point processing, multiple simultaneous scalar units and a vision-oriented, low-power instruction set.

Key Features

Fully programmable in high level languages
Scalar and Vector units to handle a mix of control and parallel code efficiently
Very Long Instruction Word (VLIW) and Single Instruction Multiple Data (SIMD) functionality
Full memory sub-system for easy integration into SOCs, utilize multi-core and hardware accelerator connectivity using standard interfaces
Automated traffic management from the system into local memories to best performance and power efficiency
Flexible precision: A combination of mixing efficient fixed-point and floating-point math

Benefits

Imitating human vision and adding computational photography to embedded systems is challenging, given the typically limited space and power resources.
To address these issues, CEVA incorporated programmable wide-vector architecture, with fixed- and floating-point processing, multiple simultaneous scalar units, and a vision-oriented low-power instruction set.
As a result, The CEVA-XM4 outperforms the most advanced GPU cluster shipping today by 33% faster processing, while consuming 9x less energy and is 17x smaller in die size.

Block Diagram

Applications

Areas of expertise relate to quality image preparation for 3D vision, image enhancement supporting various computational photography applications and generating sophisticated visual perception and video analytics from the input data.
Computer vision algorithms supported include:

Real-time 3D depth map generation
Point cloud processing
3D scanning
Object detection and tracking for example used in augmented reality (AR) applications
Object, image and scene recognition
Natural user interface applications such as face recognition, gesture recognition, user intent and emotion recognition user authentication and the like

Computational Photography algorithms supported include
Refocus image
Background replacement
Zoom
Super-resolution
Image and video stabilization
HDR
Noise reduction
Improved low-light capabilities.

Technical Specifications

Maturity

In Production

Availability

Available

Request Info