Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Improving Detection of Person Class Using Dense Pooling

Nouman Ahmad

TL;DR

This work has approached the state-of-the-art COCO datasets and extracted 6982 images that include a person object and concludes that using the approach has made significant results in detecting the person object in the given image.

Abstract

Lately, the continuous development of deep learning models by many researchers in the area of computer vision has attracted more researchers to further improve the accuracy of these models. FasterRCNN [32] has already provided a state-of-the-art approach to improve the accuracy and detection of 80 different objects given in the COCO dataset. To further improve the performance of person detection we have conducted a different approach which gives the state-of-the-art conclusion. An ROI is a step in FasterRCNN that extract the features from the given image with a fixed size and transfer into for further classification. To enhance the ROI performance, we have conducted an approach that implements dense pooling and converts the image into a 3D model to further transform into UV(ultra Violet) images which makes it easy to extract the right features from the images. To implement our approach we have approached the state-of-the-art COCO datasets and extracted 6982 images that include a person object and our final achievements conclude that using our approach has made significant results in detecting the person object in the given image

Improving Detection of Person Class Using Dense Pooling

TL;DR

This work has approached the state-of-the-art COCO datasets and extracted 6982 images that include a person object and concludes that using the approach has made significant results in detecting the person object in the given image.

Abstract

Lately, the continuous development of deep learning models by many researchers in the area of computer vision has attracted more researchers to further improve the accuracy of these models. FasterRCNN [32] has already provided a state-of-the-art approach to improve the accuracy and detection of 80 different objects given in the COCO dataset. To further improve the performance of person detection we have conducted a different approach which gives the state-of-the-art conclusion. An ROI is a step in FasterRCNN that extract the features from the given image with a fixed size and transfer into for further classification. To enhance the ROI performance, we have conducted an approach that implements dense pooling and converts the image into a 3D model to further transform into UV(ultra Violet) images which makes it easy to extract the right features from the images. To implement our approach we have approached the state-of-the-art COCO datasets and extracted 6982 images that include a person object and our final achievements conclude that using our approach has made significant results in detecting the person object in the given image

Paper Structure

This paper contains 7 sections, 2 equations, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Object Detection
  4. Proposed Models
  5. Methodology
  6. Experiments And Results
  7. Conclusion

Figures (3)

  • Figure 1: DensePose design based on Faster R-CNN with F-50 Feature Pyramid Network (FPN).
  • Figure 2: Area under ROC curve w.r.t. false positive and true positive values chosen after training the model with backbone of resnet-50 and resnet-101
  • Figure 3: Identification of human object using densePose by detection the body parts as segment