IP Cores - logiHOG

Object Detector

Key Features

  • Advanced HOG/SVM object classification core for support of Multi-Object detections in camera-based video systems
  • Supports Xilinx® Zynq®-7000 All Programmable SoC
  • ARM® AMBA® AXI4-Stream Slave compliant video input
  • AXI4-Lite compliant registers interface
  • Supports resolutions up to 4096x4096
  • Support for multiple scale detection
  • Run-time variable image size
  • High Input Data Rate; > 120 Mpixel/sec
  • High Throughput; >7.6 GMAC/sec for the classification stage
  • Low latency (< 8 lines)
  • Classifier trained on wide range of automotive scenarios
  • Prepackaged for Xilinx Vivado® Design Suite
  • Supported by advanced software training kits

This IP core can be evaluated on the logiADAK Zynq-7000 SoC Automotive Driver Assistance Kit!

Description

The logiHOG is an HOG/SVM-based object detection logicBRICKS IP core for detection of multiple objects in vision-based embedded applications. It is a direct successor of the logiPDET Pedestrian Detector IP core. The algorithm follows a discriminative approach by combining the HOG-based descriptor and the SVM classifier. HOG (Histogram of Oriented Gradients) is a descriptor designed to encode object structure. It is particularly suitable for pedestrian detection. SVM (Support Vector Machine) is a non probabilistic binary linear classifier. The core works at a single scale, i.e. the classifier is trained to recognize object at a fixed size. Extension to multiple scales is given by inserting the core in a framework that provides a sequence of re-scaled versions of the same input frame. This way it is possible to detect objects moving in an arbitrary range of distance.

embedded Vision Systems
The logiHOG core is sourced from Technology Partner
eVS embedded Vision Systems Srl.

Copyright © 2017 Xylon d.o.o.