scholarly journals Efficient Object Detection Model for Real-time UAV Application

2021 ◽  
Vol 14 (1) ◽  
pp. 45
Author(s):  
Subrahmanyam Vaddi ◽  
Dongyoun Kim ◽  
Chandan Kumar ◽  
Shafqat Shad ◽  
Ali Jannesari
Keyword(s):  
Object Detection ◽  
Real Time ◽  
High Performance ◽  
Class Imbalance ◽  
Detection Techniques ◽  
Detection Model ◽  
Deep Feature ◽  
Proposed Model ◽  
Negative Effect ◽  
Feature Pyramid

Unmanned Aerial Vehicles (UAVs) equipped with vision capabilities have become popular in recent years. Many applications have especially been employed object detection techniques extracted from the information captured by an onboard camera. However, object detection on UAVs requires high performance, which has a negative effect on the result. In this article, we propose a deep feature pyramid architecture with a modified focal loss function, which enables it to reduce the class imbalance. Moreover, the proposed method employed an end to end object detection model running on the UAV platform for real-time application. To evaluate the proposed architecture, we combined our model with Resnet and MobileNet as a backend network, and we compared it with RetinaNet and HAL-RetinaNet. Our model produced a performance of 30.6 mAP with an inference time of 14 fps. This result shows that our proposed model outperformed RetinaNet by 6.2 mAP.

scholarly journals TF-YOLO: An Improved Incremental Network for Real-Time Object Detection

2019 ◽  
Vol 9 (16) ◽  
pp. 3225 ◽  
Author(s):  
He ◽  
Huang ◽  
Wei ◽  
Li ◽  
Guo
Keyword(s):  
Embedded System ◽  
Object Detection ◽  
Real Time ◽  
Visual Detection ◽  
Portable Devices ◽  
Detection Model ◽  
Multi Scale ◽  
Art Object ◽  
Feature Pyramid ◽  
Small Targets

In recent years, significant advances have been gained in visual detection, and an abundance of outstanding models have been proposed. However, state-of-the-art object detection networks have some inefficiencies in detecting small targets. They commonly fail to run on portable devices or embedded systems due to their high complexity. In this workpaper, a real-time object detection model, termed as Tiny Fast You Only Look Once (TF-YOLO), is developed to implement in an embedded system. Firstly, the k-means++ algorithm is applied to cluster the dataset, which contributes to more excellent priori boxes of the targets. Secondly, inspired by the multi-scale prediction idea in the Feature Pyramid Networks (FPN) algorithm, the framework in YOLOv3 is effectively improved and optimized, by three scales to detect the earlier extracted features. In this way, the modified network is sensitive for small targets. Experimental results demonstrate that the proposed TF-YOLO method is a smaller, faster and more efficient network model increasing the performance of end-to-end training and real-time object detection for a variety of devices.

An Opcode-Based Malware Detection Model Using Supervised Learning Algorithms

2021 ◽  
Vol 15 (4) ◽  
pp. 18-30
Author(s):  
Om Prakash Samantray ◽  
Satya Narayan Tripathy
Keyword(s):  
Supervised Learning ◽  
Learning Algorithms ◽  
Malware Detection ◽  
Support Vector ◽  
Detection Accuracy ◽  
Detection Techniques ◽  
Detection Model ◽  
Proposed Model ◽  
Tree Classifier ◽  
Supervised Learning Algorithms

There are several malware detection techniques available that are based on a signature-based approach. This approach can detect known malware very effectively but sometimes may fail to detect unknown or zero-day attacks. In this article, the authors have proposed a malware detection model that uses operation codes of malicious and benign executables as the feature. The proposed model uses opcode extract and count (OPEC) algorithm to prepare the opcode feature vector for the experiment. Most relevant features are selected using extra tree classifier feature selection technique and then passed through several supervised learning algorithms like support vector machine, naive bayes, decision tree, random forest, logistic regression, and k-nearest neighbour to build classification models for malware detection. The proposed model has achieved a detection accuracy of 98.7%, which makes this model better than many of the similar works discussed in the literature.

Prediction of Crime Scene Objects Using Deep Learning

2021 ◽  
Vol 9 (VIII) ◽  
pp. 857-864
Author(s):  
Vibhavari B Rao
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Computer Architecture ◽  
Real Time ◽  
Surveillance System ◽  
Crime Scene ◽  
Detection Model ◽  
Detection Algorithms ◽  
Performance Metric ◽  
Smart Surveillance

The crime rates today can inevitably put a civilian's life in danger. While consistent efforts are being made to alleviate crime, there is also a dire need to create a smart and proactive surveillance system. Our project implements a smart surveillance system that would alert the authorities in real-time when a crime is being committed. During armed robberies and hostage situations, most often, the police cannot reach the place on time to prevent it from happening, owing to the lag in communication between the informants of the crime scene and the police. We propose an object detection model that implements deep learning algorithms to detect objects of violence such as pistols, knives, rifles from video surveillance footage, and in turn send real-time alerts to the authorities. There are a number of object detection algorithms being developed, each being evaluated under the performance metric mAP. On implementing Faster R-CNN with ResNet 101 architecture we found the mAP score to be about 91%. However, the downside to this is the excessive training and inferencing time it incurs. On the other hand, YOLOv5 architecture resulted in a model that performed very well in terms of speed. Its training speed was found to be 0.012 s / image during training but naturally, the accuracy was not as high as Faster R-CNN. With good computer architecture, it can run at about 40 fps. Thus, there is a tradeoff between speed and accuracy and it's important to strike a balance. We use transfer learning to improve accuracy by training the model on our custom dataset. This project can be deployed on any generic CCTV camera by setting up a live RTSP (real-time streaming protocol) and streaming the footage on a laptop or desktop where the deep learning model is being run.

scholarly journals Object Detection Techniques in Videos

2019 ◽  
Vol 9 (2S) ◽  
pp. 616-620
Keyword(s):  
Anomaly Detection ◽  
Object Detection ◽  
Real Time ◽  
Pedestrian Detection ◽  
Research Attention ◽  
Detection Techniques ◽  
Future Work

Object detection in videos has increased its popularity because of its wider applications. It has gained more research attention now days as it is applicable in real time situations like pedestrian detection, anomaly detection, Self moving cars, sports, counting of people etc. This paper begins with the introduction of object detection and briefs the basic steps in the process. It also provides a review of various techniques and approaches used for object detection in videos. Discussion of every approach and limitations will provide several promising directions and guidelines for future work.

scholarly journals An Enhanced Hidden Semi-Markov model for Outlier Detection in Multivariate Datasets

2021 ◽  
Author(s):  
G Manoharan ◽  
K Sivakumar
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Outlier Detection ◽  
Hidden Markov ◽  
Research Work ◽  
Detection Accuracy ◽  
Detection Techniques ◽  
Detection Model ◽  
Huge Data ◽  
Proposed Model

Outlier detection in data mining is an important arena where detection models are developed to discover the objects that do not confirm the expected behavior. The generation of huge data in real time applications makes the outlier detection process into more crucial and challenging. Traditional detection techniques based on mean and covariance are not suitable to handle large amount of data and the results are affected by outliers. So it is essential to develop an efficient outlier detection model to detect outliers in the large dataset. The objective of this research work is to develop an efficient outlier detection model for multivariate data employing the enhanced Hidden Semi-Markov Model (HSMM). It is an extension of conventional Hidden Markov Model (HMM) where the proposed model allows arbitrary time distribution in its states to detect outliers. Experimental results demonstrate the better performance of proposed model in terms of detection accuracy, detection rate. Compared to conventional Hidden Markov Model based outlier detection the detection accuracy of proposed model is obtained as 98.62% which is significantly better for large multivariate datasets.

scholarly journals Object detection in real time based on improved single shot multi-box detector algorithm

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Ashwani Kumar ◽  
Zuopeng Justin Zhang ◽  
Hongbo Lyu
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Single Layer ◽  
Single Shot ◽  
Convolutional Network ◽  
Detection Techniques ◽  
Computational Performance ◽  
Speed Up

Abstract In today’s scenario, the fastest algorithm which uses a single layer of convolutional network to detect the objects from the image is single shot multi-box detector (SSD) algorithm. This paper studies object detection techniques to detect objects in real time on any device running the proposed model in any environment. In this paper, we have increased the classification accuracy of detecting objects by improving the SSD algorithm while keeping the speed constant. These improvements have been done in their convolutional layers, by using depth-wise separable convolution along with spatial separable convolutions generally called multilayer convolutional neural networks. The proposed method uses these multilayer convolutional neural networks to develop a system model which consists of multilayers to classify the given objects into any of the defined classes. The schemes then use multiple images and detect the objects from these images, labeling them with their respective class label. To speed up the computational performance, the proposed algorithm is applied along with the multilayer convolutional neural network which uses a larger number of default boxes and results in more accurate detection. The accuracy in detecting the objects is checked by different parameters such as loss function, frames per second (FPS), mean average precision (mAP), and aspect ratio. Experimental results confirm that our proposed improved SSD algorithm has high accuracy.

scholarly journals Oceanic Mesoscale Eddy Detection Method Based on Deep Learning

2019 ◽  
Vol 11 (16) ◽  
pp. 1921 ◽  
Author(s):  
Zijun Duo ◽  
Wenke Wang ◽  
Huizan Wang
Keyword(s):  
Object Detection ◽  
Detection Method ◽  
Mesoscale Eddy ◽  
Mesoscale Eddies ◽  
Threshold Value ◽  
Small Samples ◽  
Automatic Identification ◽  
Detection Model ◽  
Matter Transport ◽  
Feature Pyramid

Oceanic mesoscale eddies greatly influence energy and matter transport and acoustic propagation. However, the traditional detection method for oceanic mesoscale eddies relies too much on the threshold value and has significant subjectivity. The existing machine learning methods are not mature or purposeful enough, as their train set lacks authority. In view of the above problems, this paper constructs a mesoscale eddy automatic identification and positioning network—OEDNet—based on an object detection network. Firstly, 2D image processing technology is used to enhance the data of a small number of accurate eddy samples annotated by marine experts to generate the train set. Then, the object detection model with a deep residual network, and a feature pyramid network as the main structure, is designed and optimized for small samples and complex regions in the mesoscale eddies of the ocean. Experimental results show that the model achieves better recognition compared to the traditional detection method and exhibits a good generalization ability in different sea areas.

Sign in / Sign up

Export Citation Format

Share Document