sarbjeet78 Goto Github PK

3d-cnn-action-recognition

Implementation of Action Recognition using 3D Convnet on UCF-101 dataset.

actionai

custom human activity recognition modules by pose estimation and cascaded inference using sklearn API

aiortc

WebRTC and ORTC implementation for Python using asyncio

aiortc-broadcast-demo

Broadcast your camera's video feed to many peers.

awesome-crowd-counting

Awesome Crowd Counting

b-har_baseline-human-activity-recognition

This package focuses on the definition, standardization, and development of workflow for human activity recognition in depth analysis.

boaz-adv-project

빅데이터 연합동아리 BOAZ 12기 ADV Vision 팀 [Fight Detection] 레포지토리입니다.

cocoapi

COCO API - Dataset @ http://cocodataset.org/

copy-file-from-one-folder-to-another-python

Script to search a file in a particular directory and copy that file from that directory to a destination folder

darknet

YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )

darknet_yolo_uav

dronet

DroNet: Efficient convolutional neural network detector for Real-Time UAV applications

edge-detector

A human fighting detector suit for edge devices using Tensorflow Object Detection API

event-detection-in-classroom

In this repository the events in the classroom like sit, stand, walk and fight are detected and labelled.

fight-detection

This repository is made as a part of ACM month of code, NIT Surat. It contains different algorithms to detect fight from videos like CRNN and POSENET.

fight-detection-surv-dataset

New generated dataset for fight detection in surveillance cameras.

fight_detection

Real time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition

finalrelease-uav-telelab-meity

fire-detection-cnn

real-time fire detection in video imagery using a convolutional neural network (deep learning) - from our ICIP 2018 paper (Dunnings / Breckon) + ICMLA 2019 paper (Samarth / Bhowmik / Breckon)

fire-detection-image-dataset

This dataset contains normal images and images with fire. It is highly unbalanced to reciprocate real world situations. It consists of a variety of scenarios and different fire situations (intensity, luminosity, size, environment etc).

fire-smoke-detect-yolov4

fire-smoke-detect-yolov4-yolov5 and fire-smoke-detection-dataset 火灾检测，烟雾检测

google-ava-dataset-downloader

国内下载google AVA dataset;download google AVA dataset in China

hr-mscnn

a HR-based multi-stream CNN descriptor (HR-MSCNN) is formulated to recognize human action

human-activity-dih18

Human Activity Recognition Using Deep Neural Network

human-activity-recgnition

We worked on action recognition in search and rescue using drone surveillance. Our aim was to classify a video on help or non-help class. Which can be used during a disaster as at many places people can’t reach to check if there is any person needing help but the drone can search the area and notify the location to the rescue team. The data set we used was UCF 101 dataset(contained 101 different classes over 13k video clips) and Help Non-Help data set which was collected by the drone by one of our mentors. The first which we used was the CNN in which we attempted to classify each video based on a single frame. Also we used Inception V3 which was pretrained on imagenet dataset .(also known as transfer learning) Now instead of just classifying based on CNN model,we used CNN+RNN. Now the features extracted from inception V3,we convert those extracted features into sequences of extracted features and then are passed to LSTM after removing the top classification layer.on which we got 89.74% of accuracy.

human-activity-recognition

Recognizing human activities using Deep Learning

human_activity_recognition

A new and computationally cheap method to perform human activity recognition using PoseNet and LSTM. Where we use PoseNet for Preprocessing and LSTM for understand the sequence.

latetemporalmodeling3dcnn

learnopencv

Learn OpenCV : C++ and Python Examples

lightweight-human-pose-estimation.pytorch

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.