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