26 skills found
tau-adl / Detection Tracking JetsonTX2Real-time Drone Visual Detection and Tracking algorithm based on YOLOv3 and GOTURN.
floodsung / Tracking On IOSTest Several Visual Object Tracking Algorithm including CMT,TLD,CT on iOS
itsShnik / VisualObjectTrackingVisual Object Tracking algorithms. Hold on! There is a lot to come
chs74515 / PeopleCounterIn present days, people detection, tracking and counting is an important aspect in the video investigation and subjection demand in Computer Vision Systems. Providing (real time) traffic information will help improve and reduce pedestrian and vehicle traffic, especially when the data collected is learned and analyzed over a period of time, which makes its highly essential to identify people, vehicles and objects in general and also accurately counting the number of people and/or vehicles entering and leaving a particular location in real time. To perform people counting, a robust and efficient system is needed. This research is aimed at making a pedestrian traffic reporting system for certain areas and buildings around the campus to potentially help ease traffic circulation. Providing this information will be done through a developed application, which includes image processing with Open Computer Vision (OpenCV). This will show the amount of traffic in certain buildings or area over a period of time. OpenCV is a cross-platform library which can be used to develop real-time Computer Vision applications [Opencv, 2015b]. It is mainly focused on image processing, video capture and analysis including features like people and object detection. The operations performed were based on the performance and accuracy of the tracking algorithms when implemented in embedded devices such as the Raspberry Pi and the Tinker Board. The Pi Camera was used for real time vision and hosted on the embedded device. The proposed method used was conjoined with an open-source visual tracking implementation from the contribution branch of the OpenCV library and a unique technique for people detection along with different Filtering Algorithms for tracking this. The programming language of choice to implement these features (Tracking and Detection) is python and its libraries. The present work describes a standalone people counting application designed using Python OpenCV and tested on embedded devices ranging from the Raspberry Pi3 to a Tinker Board and a compatible Camera. All these were used in prototyping the design of this application. The results reported and showed that the Person-Counter system developed counted the number of people entering the designated area (down), and the number of people leaving (up).
JanghoonChoi / TACTVisual Tracking by TridenAlign and Context Embedding
DFRobot / Pxt DFRobot HuskyLensHuskyLens is an easy-to-use ai vision sensor with six built-in functions: face recognition, object tracking, object recognition, line tracking, color recognition, and label (qr code) recognition. Only one button is needed to complete the AI training, which can get rid of tedious training and complicated visual algorithm, and make you more focused on the conception and implementation of the project.
AKAGIwyf / UAV TrackingIn recent years, UAV began to appear in all aspects of production and life of human society, and has been widely used in aerial photography, monitoring, security, disaster relief and other fields. For example, UAV tracking can be used for urban security, automatic cruise to find suspects and assist in intelligent urban security management.However, the practical application of UAV in various early scenes was mostly based on human remote control or intervention, and the degree of automation was not high. The degree to which UAVs can be automated is one of the decisive factors in whether they can play a bigger role in the future. With the increasing demand of UAV automation, target tracking based on computer vision has become one of the current research hotspots. Some companies in China and abroad, such as DJI, have successfully equipped target tracking on UAVs, but these technologies only exist in papers and descriptions, and the specific implementation has not been sorted out and opened source. Therefore, we plan to try to complete this project by ourselves and open source it on Github. Traditional visual tracking has many advantages, such as strong autonomy, wide measurement range and access to a large amount of environmental information, it also has many disadvantages.It requires a powerful hardware system. In order to obtain accurate navigation information, it needs to be equipped with a high-resolution camera and a powerful processor. From image data acquisition to processing, huge data operations are involved, which undoubtedly increases the cost of UAV tracking. Moreover, the reliability of traditional visual navigation and tracking is poor, and it is difficult for UAV to work in complex lighting and obstacle scenes. Therefore, we plan to use deep learning for target tracking in this project. We can train our own model through deep learning algorithm (we have not decided what network structure to use), then move the trained model to the embedded development board for operation, fix it on the UAV, read the image through the camera and process the data, so that it can recognize the objects to be recognized and tracked. In this project, we will use NVIDIA Jetson TX2 development board, install ROS in Linux system, establish communication with pixhawk, and conduct UAV flight control through PID algorithm.
neohanju / OnlineMCMTTOnline Multiple Camera Multiple Target Tracking Algorithm implemented by Visual C++
lukacu / Visual Tracking MatlabMatlab code for several visual tracking algorithms
SHI-Yu-Zhe / Single Object Visual Tracking A Paper ListA complete paper list of Single-Object Visual Tracking Algorithms, Surveys and Benchmarks of recent years. Different from existing paper list, this project doesn't simply category the papers by publishment, but from a tracking challenge-tackling perspective.
George-Zhuang / AI FlyingAn introduction to AI methods for flying agents (birds, UAVs, etc.)
vicoslab / LegitLegit is a C++ library that contains implementations of various visual tracking algorithms.
maazmb / LEP Hybrid Visual OdometryWe propose a novel real time monocular Hybrid visual odometry formulation which combines the high precision of indirect approaches with the fast performance of direct methods. The system initializes inverse depth estimates represented as a Gaussian probability distribution for features (lines, edges and points) extracted in each keyframe which we continuously propagate and update with new measurements in the following frames. The key idea is to incorporate the depth filter distributions into the initial pose tracking via sparse image alignment and also the pose refinement via map localization. We also propose a comprehensive initialization method of these depth filters and classify the map points into different categories based on the uncertainty of these depth estimates which as a result greatly improves the tracking performance. The experimental evaluation on benchmark datasets shows that the proposed approach is significantly faster than the state-of-the-art algorithms while achieving comparable accuracy. We make our implementation publically open source at github to provide as a valuable reference for the SLAM community.
MPKowalczyk / MOSSE XOHIn this project a hardware-software implementation of adaptive correlation filter tracking for a 3840 x 2160 @ 60 fps video stream in a Zynq UltraScale+ MPSoC is discussed. Correlation filters gained popularity in recent years because of their efficiency and good results in the VOT (Visual Object Tracking) challenge. An implementation of the MOSSE (Minimum Output Sum of Squared Error) algorithm is presented. It utilizes 2-dimensional FFT for computing correlation and updates filter coefficients in every frame. The initial filter coefficients are computed on the ARM processor in the PS (Processing System), while all other operations are preformed in PL (Programmable Logic). The presented architecture was described with the use of Verilog hardware description language.
chkap / CrtA visual object tracking algorithm based on convolutional regression framework
anunay2608 / DLVSA novel deep learning based visual servoing architecture “DLVS” is proposed for control of an unmanned aerial vehicle (UAV) capable of quasi-stationary flight with a camera mounted under the vehicle to track a target consisting of a finite set of stationary points lying in a plane. Current Deep Learning and Reinforcement Learning (RL) based end-to-end servoing approaches rely on training convolutional neural networks using color images with known camera poses to learn the visual features in the environment suitable for servoing tasks. This approach limits the application of the network to known environments where the dataset was collected, moreover such networks cannot be deployed on the low power computers present on board the UAV. The proposed solution employs a time series architecture to learn temporal data from sequential values to output the control ques to the flight controller. The low computational complexity and flexibility of the DLVS architecture ensures real time on board tracking for virtually any target. The algorithm was thoroughly validated in real-life environments and outperformed the current state-of-the-arts in terms of both time efficiency and accuracy.
connahKendrickMMU / Towards Real Time Facial Landmark Detection In Depth Data Using Auxiliary InformationModern facial motion capture systems employ a two-pronged approach for capturing and rendering facial motion. Visual data (2D) is used for tracking the facial features and predicting facial expression, whereas Depth (3D) data is used to build a series of expressions on a 3D face models. An issue with modern research approaches is the use of a single data stream that provides little indication of the 3D facial structure. We compare and analyse the performance of Convolutional Neural Networks (CNN) using visual, Depth and merged data to identify facial features in real-time using a Depth sensor. First, we review the facial landmarking algorithms and its datasets for Depth data. We address the limitation of the current datasets by introducing the Kinect One Expression Dataset (KOED). Then, we propose the use of CNNs for the single data stream and merged data streams for facial landmark detection. We contribute to existing work by performing a full evaluation on which streams are the most effective for the field of facial landmarking. Furthermore, we improve upon the existing work by extending neural networks to predict into 3D landmarks in real-time with additional observations on the impact of using 2D landmarks as auxiliary information. We evaluate the performance by using Mean Square Error (MSE) and Mean Average Error (MAE). We observe that the single data stream predicts accurate facial landmarks on Depth data when auxiliary information is used to train the network.
BhavyanshM / LineEstimatorVision-based Line Estimation and Tracking algorithms for Visual Odometry and SLAM
liminglong / Tld Turtlebot FollowerThis is a ROS package, which can make the turtlebot follow an pre-selected object. The visual tracking algorithm is TLD.
Tanaybalraj / Eye Blink To SpeechMotor Neuron Disease (MND) is a medical condition where the motor neurons of the patient are paralyzed, it is incurable. It also leads to weakness of muscles with respect to hand, feet or voice. Because of this, the patient cannot perform his voluntary actions and it is very difficult for the patient to express his needs as he is not able to communicate with the world. There are many methods introduced for the motor neuron disease patients to communicate with the outside world such as Brain wave technique and Electro-oculography. Loss of speech can be hard to adjust. It is difficult for the patients to make the caretaker understand what they need especially when they are in hospitals. It becomes difficult for the patients to express their feelings and even they cannot take part in conversations. System incorporates different visual technologies, such as eye blink detection, eye centre localization and conversion of the eye blink to speech. The proposed system detects the eye blink and differentiates between an intentional long blink and a normal eye blink. The proposed system can be used to control and Communicate with other people. The objectives of the system are: Capturing the frame from the video using the system’s camera initialises the execution of the proposed system.The Face Detection Algorithm then processes on the captured video frames to give out the rectangular boxed face. This output from Face Detection Algorithm then gets processed using AdaBoost Classifier to detect the eye region in the face.Eye detected will be sent to check if there is any movement of the eyeball. If it’s there, then this movement will be tracked to give out the combination the patient is using to express the dialogue.If not, then the blink pattern will be processed to give out the voice as well as the text input with respective dialogue.
