Universal Object Detection Architecture (UOD)

Phi Algorithm Solutions Inc. will be developing a series of  Object Detectors all based on a common architecture.  This efficient architecture requires no preprocessing on subwindows, and therefore allows a high degree of resource sharing allowing for a streamlined dataflow.  Moreover, by simply changing coefficients within the architecture, any type of arbitrary  high performance detector can be achieved.

FD-1 Face Detector

The FD-1 is a general face detector and first in a series of object detectors based on the UOD architecture.  This detector is robust to a number of slight image distortions including in-plane rotation, out-of-plane rotations, translational motion, Gaussian noise, compression artefacts, poor contrast or non-uniform lighting, partial occlusions and oversmoothing.   The FD-1 detector attains a good balance of detection rates vs false alarms while remaining flexible with a high degree of programmability. 

PD-1 Pedestrian Detection and Tracking

The PD-1 is a pedestrian detector and tracker that leverages the existing UOD architecture.  This technology is a combination of three main functions: foreground extraction, pedestrian detection, and object tracking.  The PD-1 is robust to a number of slight image distortions and can be mapped to a number of implementations including CPU, DSP, RTL, and GPU. 

Pedestrian Demo with CNN