deployment of a hybrid model for automatic weapon detection/ anomaly detection for surveillance applications

Overview

Automatic Weapon Detection

Deployment of a hybrid model for automatic weapon detection/ anomaly detection for surveillance applications.

Stars Badge Forks Badge Pull Requests Badge Issues Badge GitHub contributors License   Badge


Loved the project? Please visit our Website


Literature Survey

Security is always a main concern in every domain, due to a rise in crime rate in a crowded event or suspicious lonely areas. Weapon detection and monitoring have major applications of computer vision to tackle various problems. Due to growing demand in the protection of safety, security and personal properties, needs and deployment of video surveillance systems can recognize and interpret the scene and anomaly events play a vital role in intelligence monitoring. We implemented weapon detection using a convolution neural network (CNN). Results are tabulated, both algorithms achieve good accuracy, but their application in real situations can be based on the trade-off between speed and accuracy. We surveyed various research evidences and proposed a detection framework which involves three phases detection of objects, recognition of detected objects and alarm system. Single learning based detection framework is used because of which high processing speed is achieved. Because dense features need only to be evaluated once rather than individually for each detector. For object detection a framework using a linear support vector machine classifier with histogram of oriented gradients features. Using a combination of ACF(Aggregated Channel Features) features and sp- LBP(Local binary pattern)features can provide a better trade-off between detection performance and system runtime. some techniques are used to post-process raw detection results. Uses shrinkage version of AdaBoost as the strong classifier and use decision trees as weak learners.To train the classifier, the procedure known as bootstrapping is applied . Shifu Zhou(researcher) et al suggested a method for detecting and locating anomalous activities in video sequences of crowded scenes. The key for method is the coupling of anomdescribon with a spatial-temporal Convolutional Neural Networks. This architecture allows us to capture features from both spatial and temporal dimensions by performing spatial-temporal convolutions, thereby, both the appearance and motion information encoded in continuous frames are extracted Two criterions are used for evaluating anomaly detection accuracy namely a frame level criterion and a pixel level criterion. Motion pattern and FRP (False positive rates) are calculated for evaluating performance. And DR(Detection Rate) corresponds to the successful detection rate of the anomalies happening at EER(Equal Error Rate). We also surveyed from various research evidences that One of the main challenges is to detect anomalies both in time and space domains. This implies to find out which frames that anomalies occur and to localize regions that generate the anomalies within these frames. This model extracts features from both the spatial and the temporal dimensions by performing. 3D convolutions, is achieved by convolving a 3D kernel to the cube formed by stacking multiple contiguous frames together. The issues are that , accurate recognition of actions is a highly challenging task due to cluttered backgrounds, occlusions, and viewpoint variations perform 3D convolution in the convolutional layers of CNNs so that discriminative features along both the spatial and the temporal dimensions are captured.3D convolution is achieved by stacking multiple contiguous frames together. The developed 3D CNN model was trained using a supervised algorithm , and it requires a large number of labelled samples. we propose a novel end-to-end model which integrates the one-class Support Vector Machine (SVM) into Convolutional Neural Network (CNN). Specifically, the robust loss function derived from the one-class SVM is proposed to optimize the parameters of this model. We proposed a learning model for weapon detection from video sequences by combining CNN and SVM. CNN is utilized to learn the underlying high-dimensional normal representations to effectively capture normal features. SVM layer not only distinguishes normal/abnormal cases as a discriminator, but also optimizes parameters of the whole model as an optimization objective. From our exhaustive study of work done and research about Weapon detection model , we proposed a Model which detects the Weapon from video or Picture and activates the alarm.

Features to Detect Weapons / Intruders

Weapons:

We propose algorithms that are able to alert the human operator when a firearm or knife is visible in the image. We have focused on limiting the number of false alarms in order to allow for a real-life application of the system. The specificity and sensitivity of the knife detection are significantly better than others published recently. We have also managed to propose a version of a firearm detection algorithm that offers a near-zero rate of false alarms. We have shown that it is possible to create a system that is capable of an early warning in a dangerous situation, which may lead to faster and more effective response times and a reduction in the number of potential victims.

Size:

Estimation of the size of software is an essential part of Software Project Management. It helps the project manager to further predict the effort and time which will be needed to build the project. Various measures are used in project size estimation. Some of these are: • Lines of Code • Number of entities in ER diagram • Total number of processes in detailed data flow diagram • Function points

Find the number of functions belonging to the following types: • External Inputs: Functions related to data entering the system. • External outputs: Functions related to data exiting the system. • External Inquiries: They leads to data retrieval from system but don’t change the system. • Internal Files: Logical files maintained within the system. Log files are not included here. • External interface Files: These are logical files for other applications which are used by our system.

Trigger:

Detecting small objects is a difficult task as these objects are rather smaller than the human. In this section, we will implement a gun detector that trained by using the discriminatively trained part-based models. As our object of interest is gun, we will collect different positive samples from different type of gun related videos. To minimize the amount of supervision, we provide the bounding box of the gun in the first frame where the gun appears and apply the tracking method to let it track for the gun. We will then use the result from the tracker to annotate the gun location in each image. For the negative samples, we will use all the annotation from the Pascal Visual Object Classes Challenge (VOC) as all the annotations are without any gun object. Lastly, all the annotation results of the positive sample and negative samples are used as the input for the DPM to train a gun model. Tracking is required in different stages of our system because the object detector tends to produce sparse detection as the object of interest is too small.

Handle

Cohen’s kappa coefficient is used to check the agreement between experts which is calculated using following formula:

aaaaa

where pa ¼ proportion of observations for agreement of two experts; pc ¼ proportion of observations for agreement which is expected to happen by chance between two experts. Agreement matrix of proportions is for weapon purchase. Cohen’ Kappa coefficient value was found to be 0.9425 at a ¼ 0.05 (a is probability of confidence interval for kappa statistics) which signifies an almost perfect agreement between the experts. R Programming Package “psych” is used to compute Cohen’s kappa coefficient. Considering significance and magnitude of kappa coefficient so computed, the annotations labelling represents the justification of process of manually labelling approach which can therefore be used in our analysis to train and test our proposed automated illegal weapon procurement model.

Project Summary:

In this project CNN algorithm is simulated for pre-labelled image dataset for weapon (gun, knife) detection. The algorithm is efficient and gives good results but its application in real time is based on a trade-off between speed and accuracy. With respect to accuracy, CNN gives accuracy of approx. 85%. In our CNN model we have taken 16 layers. Apart from this the optimiser used by us is SGD, with categorical cross entropy loss and accuracy is used as the metrics. For every layer we have used the ‘relu’ activation function, for the last layer we have used softmax. We have used Tensorflow, Keras, PIL, OpenCV, Playsound modules to implement the project. Our software takes a 240 x 240 image as input, in a batch size of 32.

Further, it can be implemented for larger datasets by training using GPUs and high-end DSP and FPGA kits.

Owner
Janhavi
Janhavi
Use Convolutional Recurrent Neural Network to recognize the Handwritten line text image without pre segmentation into words or characters. Use CTC loss Function to train.

Handwritten Line Text Recognition using Deep Learning with Tensorflow Description Use Convolutional Recurrent Neural Network to recognize the Handwrit

sushant097 224 Jan 07, 2023
The official code for the ICCV-2021 paper "Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates".

SpeechDrivesTemplates The official repo for the ICCV-2021 paper "Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates". [arxiv

Qian Shenhan 53 Dec 23, 2022
This is a GUI program which consist of 4 OpenCV projects

Tkinter-OpenCV Project Using Tkinter, Opencv, Mediapipe This is a python GUI program using Tkinter which consist of 4 OpenCV projects 1. Finger Counte

Arya Bagde 3 Feb 22, 2022
scantailor - Scan Tailor is an interactive post-processing tool for scanned pages.

Scan Tailor - scantailor.org This project is no longer maintained, and has not been maintained for a while. About Scan Tailor is an interactive post-p

1.5k Dec 28, 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
Handwritten Text Recognition (HTR) using TensorFlow 2.x

Handwritten Text Recognition (HTR) system implemented using TensorFlow 2.x and trained on the Bentham/IAM/Rimes/Saint Gall/Washington offline HTR data

Arthur Flôr 160 Dec 21, 2022
Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

Total-Text-Dataset (Official site) Updated on April 29, 2020 (Detection leaderboard is updated - highlighted E2E methods. Thank you shine-lcy.) Update

Chee Seng Chan 671 Dec 27, 2022
The virtual calculator will be above the live streaming from your camera

The virtual calculator is above the live streaming from my camera usb , the program first detect my hand and in each frame calculate the distance between two finger ,if the distance is lower than the

gasbaoui mohammed al amine 5 Jul 01, 2022
pulse2percept: A Python-based simulation framework for bionic vision

pulse2percept: A Python-based simulation framework for bionic vision Retinal degenerative diseases such as retinitis pigmentosa and macular degenerati

67 Dec 29, 2022
A curated list of papers, code and resources pertaining to image composition

A curated list of resources including papers, datasets, and relevant links pertaining to image composition.

BCMI 391 Dec 30, 2022
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
Character Segmentation using TensorFlow

Character Segmentation Segment characters and spaces in one text line,from this paper Chinese English mixed Character Segmentation as Semantic Segment

26 Aug 25, 2022
Some bits of javascript to transcribe scanned pages using PageXML

nashi (nasḫī) Some bits of javascript to transcribe scanned pages using PageXML. Both ltr and rtl languages are supported. Try it! But wait, there's m

Andreas Büttner 15 Nov 09, 2022
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched or copy-pasted. ocrmypdf # it's a scriptable c

jbarlow83 7.9k Jan 03, 2023
Drowsiness Detection and Alert System

A countless number of people drive on the highway day and night. Taxi drivers, bus drivers, truck drivers, and people traveling long-distance suffer from lack of sleep.

Astitva Veer Garg 4 Aug 01, 2022
Code for the paper: Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution

Fusformer Code for the paper: "Fusformer: A Transformer-based Fusion Approach for Hyperspectral Image Super-resolution" Plateform Python 3.8.5 + Pytor

Jin-Fan Hu (胡锦帆) 11 Dec 12, 2022
Code for the ACL2021 paper "Combining Static Word Embedding and Contextual Representations for Bilingual Lexicon Induction"

CSCBLI Code for our ACL Findings 2021 paper, "Combining Static Word Embedding and Contextual Representations for Bilingual Lexicon Induction". Require

Jinpeng Zhang 12 Oct 08, 2022
STEFANN: Scene Text Editor using Font Adaptive Neural Network

STEFANN: Scene Text Editor using Font Adaptive Neural Network @ The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020.

Prasun Roy 208 Dec 11, 2022
Qrcode Attendence System with Opencv and Pyzbar

Setup process Creates a virtual environment (Scripts that ensure executed Python code uses the Python interpreter and site packages installed inside t

Ganesh 5 Aug 01, 2022
A bot that plays TFT using OCR. Keeps track of bench, board, items, and plays the user defined team comp.

NOTES: To ensure best results, make sure you are running this on a computer that has decent specs. 1920x1080 fullscreen is required in League, game mu

francis 125 Dec 30, 2022