Probabilistic Model of Object Detection Based on Convolutional Neural Network

TL;DR

This paper introduces a probabilistic model for object detection using CNNs that improves efficiency and informativeness by mapping images into probabilistic object distributions, validated through experiments.

Contribution

It proposes a novel probabilistic framework that enhances object detection by reducing computation and providing more informative outputs compared to traditional methods.

Findings

Model is sound and efficient

Experiments on FDDB validate effectiveness

Provides more informative detection outputs

Abstract

The combination of a CNN detector and a search framework forms the basis for local object/pattern detection. To handle the waste of regional information and the defective compromise between efficiency and accuracy, this paper proposes a probabilistic model with a powerful search framework. By mapping an image into a probabilistic distribution of objects, this new model gives more informative outputs with less computation. The setting and analytic traits are elaborated in this paper, followed by a series of experiments carried out on FDDB, which show that the proposed model is sound, efficient and analytic.