Code for the head detector (HeadHunter) proposed in our CVPR 2021 paper Tracking Pedestrian Heads in Dense Crowd.

Overview

Head Detector

Code for the head detector (HeadHunter) proposed in our CVPR 2021 paper Tracking Pedestrian Heads in Dense Crowd. The head_detection module can be installed using pip in order to be able to plug-and-play with HeadHunter-T.

Requirements

  1. Nvidia Driver >= 418

  2. Cuda 10.0 and compaitible CudNN

  3. Python packages : To install the required python packages; conda env create -f head_detection.yml.

  4. Use the anaconda environment head_detection by activating it, source activate head_detection or conda activate head_detection.

  5. Alternatively pip can be used to install required packages using pip install -r requirements.txt or update your existing environment with the aforementioned yml file.

Training

  1. To train a model, define environment variable NGPU, config file and use the following command

$python -m torch.distributed.launch --nproc_per_node=$NGPU --use_env train.py --cfg_file config/config_chuman.yaml --world_size $NGPU --num_workers 4

  1. Training is currently supported over (a) ScutHead dataset (b) CrowdHuman + ScutHead combined, (c) Our proposed CroHD dataset. This can be mentioned in the config file.

  2. To train the model, config files must be defined. More details about the config files are mentioned in the section below

Evaluation and Testing

  1. Unlike the training, testing and evaluation does not have a config file. Rather, all the parameters are set as argument variable while executing the code. Refer to the respective files, evaluate.py and test.py.
  2. evaluate.py evaluates over the validation/test set using AP, MMR, F1, MODA and MODP metrics.
  3. test.py runs the detector over a "bunch of images" in the testing set for qualitative evaluation.

Config file

A config file is necessary for all training. It's built to ease the number of arg variable passed during each execution. Each sub-sections are as elaborated below.

  1. DATASET

    1. Set the base_path as the parent directory where the dataset is situated at.
    2. Train and Valid are .txt files that contains relative path to respective images from the base_path defined above and their corresponding Ground Truth in (x_min, y_min, x_max, y_max) format. Generation files for the three datasets can be seen inside data directory. For example,
    /path/to/image.png
    x_min_1, y_min_1, x_max_1, y_max_1
    x_min_2, y_min_2, x_max_2, y_max_2
    x_min_3, y_min_3, x_max_3, y_max_3
    .
    .
    .
    
    1. mean_std are RGB means and stdev of the training dataset. If not provided, can be computed prior to the start of the training
  2. TRAINING

    1. Provide pretrained_model and corresponding start_epoch for resuming.
    2. milestones are epoch at which the learning rates are set to 0.1 * lr.
    3. only_backbone option loads just the Resnet backbone and not the head. Not applicable for mobilenet.
  3. NETWORK

    1. The mentioned parameters are as described in experiment section of the paper.
    2. When using median_anchors, the anchors have to be defined in anchors.py.
    3. We experimented with mobilenet, resnet50 and resnet150 as alternative backbones. This experiment was not reported in the paper due to space constraints. We found the accuracy to significantly decrease with mobilenet but resnet50 and resnet150 yielded an almost same performance.
    4. We also briefly experimented with Deformable Convolutions but again didn't see noticable improvements in performance. The code we used are available in this repository.

Note :

This codebase borrows a noteable portion from pytorch-vision owing to the fact some of their modules cannot be "imported" as a package.

Citation :

@InProceedings{Sundararaman_2021_CVPR,
    author    = {Sundararaman, Ramana and De Almeida Braga, Cedric and Marchand, Eric and Pettre, Julien},
    title     = {Tracking Pedestrian Heads in Dense Crowd},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {3865-3875}
}
Owner
Ramana Subramanyam
Ramana Subramanyam
A program that takes in the hand gesture displayed by the user and translates ASL.

Interactive-ASL-Recognition Using the framework mediapipe made by google, OpenCV library and through self teaching, I was able to create a program tha

Riddhi Bajaj 3 Nov 22, 2021
computer vision, image processing and machine learning on the web browser or node.

Image processing and Machine learning labs   computer vision, image processing and machine learning on the web browser or node note Fast Fourier Trans

ryohei tanaka 487 Nov 11, 2022
Deskew is a command line tool for deskewing scanned text documents. It uses Hough transform to detect "text lines" in the image. As an output, you get an image rotated so that the lines are horizontal.

Deskew by Marek Mauder https://galfar.vevb.net/deskew https://github.com/galfar/deskew v1.30 2019-06-07 Overview Deskew is a command line tool for des

Marek Mauder 127 Dec 03, 2022
Select range and every time the screen changes, OCR is activated.

ASOCR(Auto Screen OCR) Select range and every time you press Space key, OCR is activated. 範囲を選ぶと、あなたがスペースキーを押すたびに、画面が変わる度にOCRが起動します。 usage1: simple OC

1 Feb 13, 2022
Introduction to Augmented Reality (AR) with Python 3 and OpenCV 4.2.

Introduction to Augmented Reality (AR) with Python 3 and OpenCV 4.2.

fernanda rodríguez 85 Jan 02, 2023
A semi-automatic open-source tool for Layout Analysis and Region EXtraction on early printed books.

LAREX LAREX is a semi-automatic open-source tool for layout analysis on early printed books. It uses a rule based connected components approach which

162 Jan 05, 2023
Textboxes_plusplus implementation with Tensorflow (python)

TextBoxes++-TensorFlow TextBoxes++ re-implementation using tensorflow. This project is greatly inspired by slim project And many functions are modifie

81 Dec 07, 2022
A small C++ implementation of LSTM networks, focused on OCR.

clstm CLSTM is an implementation of the LSTM recurrent neural network model in C++, using the Eigen library for numerical computations. Status and sco

Tom 794 Dec 30, 2022
Rotational region detection based on Faster-RCNN.

R2CNN_Faster_RCNN_Tensorflow Abstract This is a tensorflow re-implementation of R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detecti

UCAS-Det 581 Nov 22, 2022
python ocr using tesseract/ with EAST opencv detector

pytextractor python ocr using tesseract/ with EAST opencv text detector Uses the EAST opencv detector defined here with pytesseract to extract text(de

Danny Crasto 38 Dec 05, 2022
This is a GUI for scrapping PDFs with the help of optical character recognition making easier than ever to scrape PDFs.

pdf-scraper-with-ocr With this tool I am aiming to facilitate the work of those who need to scrape PDFs either by hand or using tools that doesn't imp

Jacobo José Guijarro Villalba 75 Oct 21, 2022
Repository collecting all the submodules for the new PyTorch-based OCR System.

OCRopus3 is being replaced by OCRopus4, which is a rewrite using PyTorch 1.7; release should be soonish. Please check github.com/tmbdev/ocropus for up

NVIDIA Research Projects 138 Dec 09, 2022
Um simples projeto para fazer o reconhecimento do captcha usado pelo jogo bombcrypto

CaptchaSolver - LEIA ISSO 😓 Para iniciar o codigo: pip install -r requirements.txt python captcha_solver.py Se você deseja pegar ver o resultado das

Kawanderson 50 Mar 21, 2022
Script para controlar o movimento do mouse usando Python e openCV com câmera em tempo real que detecta pontos de referência da mão, rastreia padrões de gestos em vez de um mouse físico.

mouserController Script para controlar o movimento do mouse usando Python e openCV com câmera em tempo real que detecta pontos de referência da mão, r

Vinícius Azevedo 6 Jun 28, 2022
Implement 'Single Shot Text Detector with Regional Attention, ICCV 2017 Spotlight'

SSTDNet Implement 'Single Shot Text Detector with Regional Attention, ICCV 2017 Spotlight' using pytorch. This code is work for general object detecti

HotaekHan 84 Jan 05, 2022
Slice a single image into multiple pieces and create a dataset from them

OpenCV Image to Dataset Converter Slice a single image of Persian digits into mu

Meysam Parvizi 14 Dec 29, 2022
Let's explore how we can extract text from forms

Form Segmentation Let's explore how we can extract text from any forms / scanned pages. Objectives The goal is to find an algorithm that can extract t

Philip Doxakis 42 Jun 05, 2022
Hiiii this is the Spanish for Linux and win 10 and in the near future the english version of PortScan my new tool on which you can see what ports are Open only with the IP adress.

PortScanner-by-IIT PortScanner es una herramienta programada en Python3. Como su nombre indica esta herramienta escanea los primeros 150 puertos de re

5 Sep 19, 2022
Ocular is a state-of-the-art historical OCR system.

Ocular Ocular is a state-of-the-art historical OCR system. Its primary features are: Unsupervised learning of unknown fonts: requires only document im

228 Dec 30, 2022
Implementation of our paper 'PixelLink: Detecting Scene Text via Instance Segmentation' in AAAI2018

Code for the AAAI18 paper PixelLink: Detecting Scene Text via Instance Segmentation, by Dan Deng, Haifeng Liu, Xuelong Li, and Deng Cai. Contributions

758 Dec 22, 2022