Multitarget Tracking Using Siamese Neural Networks

2021 ◽  
Vol 17 (2s) ◽  
pp. 1-16
Author(s):  
Na An ◽  
Wei Qi Yan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Object Tracking ◽  
Target Tracking ◽  
Deep Neural Networks ◽  
Multitarget Tracking ◽  
Siamese Network ◽  
Single Target ◽  
Single Target Tracking

In this article, we detect and track visual objects by using Siamese network or twin neural network. The Siamese network is constructed to classify moving objects based on the associations of object detection network and object tracking network, which are thought of as the two branches of the twin neural network. The proposed tracking method was designed for single-target tracking, which implements multitarget tracking by using deep neural networks and object detection. The contributions of this article are stated as follows. First, we implement the proposed method for visual object tracking based on multiclass classification using deep neural networks. Then, we attain multitarget tracking by combining the object detection network and the single-target tracking network. Next, we uplift the tracking performance by fusing the outcomes of the object detection network and object tracking network. Finally, we speculate on the object occlusion problem based on IoU and similarity score, which effectively diminish the influence of this issue in multitarget tracking.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

scholarly journals An Efficient Multi-Path Multitarget Tracking Algorithm for Over-The-Horizon Radar

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1384 ◽  
Author(s):  
Yuan Huang ◽  
Yifang Shi ◽  
Taek Song
Keyword(s):  
Target Tracking ◽  
Signal Propagation ◽  
Multitarget Tracking ◽  
Joint Measurement ◽  
Single Target ◽  
Measurement Cell ◽  
Multiple Detection ◽  
Effectiveness And Efficiency ◽  
Measurement Path ◽  
Single Target Tracking

In target tracking environments using over-the-horizon radar (OTHR), one target may generate multiple detections through different signal propagation paths. Trackers need to jointly handle the uncertainties stemming from both measurement origin and measurement path. Traditional multitarget tracking algorithms suffer from high computational loads in such environments since they need to enumerate all possible joint measurement-to-track assignments considering the measurements paths unless they employ some approximations regarding the measurements and their corresponding paths. In this paper, we propose a novel algorithm, named multi-path linear multitarget integrated probabilistic data association (MP-LM-IPDA), to efficiently track multitarget in multiple detection environments. Instead of generating all possible joint assignments, MP-LM-IPDA calculates the modulated clutter measurement density for each measurement cell of each track. The modulated clutter measurement density considers the possibility that the measurement cells originate from the clutter as well as from other potential targets. By incorporating the modulated clutter measurement density, the single target tracking structure can be applied for multitarget tracking, which significantly reduces the computational load. The simulation results demonstrate the effectiveness and efficiency of the proposed algorithm.

scholarly journals Surrogate Object Detection Explainer (SODEx) with YOLOv4 and LIME

2021 ◽  
Vol 3 (3) ◽  
pp. 662-671
Author(s):  
Jonas Herskind Sejr ◽  
Peter Schneider-Kamp ◽  
Naeem Ayoub
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Deep Neural Networks ◽  
Empirical Evaluation ◽  
Network Models ◽  
Detection Algorithm ◽  
Neural Network Models ◽  
The Neural Network

Due to impressive performance, deep neural networks for object detection in images have become a prevalent choice. Given the complexity of the neural network models used, users of these algorithms are typically given no hint as to how the objects were found. It remains, for example, unclear whether an object is detected based on what it looks like or based on the context in which it is located. We have developed an algorithm, Surrogate Object Detection Explainer (SODEx), that can explain any object detection algorithm using any classification explainer. We evaluate SODEx qualitatively and quantitatively by detecting objects in the COCO dataset with YOLOv4 and explaining these detections with LIME. This empirical evaluation does not only demonstrate the value of explainable object detection, it also provides valuable insights into how YOLOv4 detects objects.

scholarly journals Bird Detection using Siamese Neural Network

2020 ◽  
Vol 9 (7) ◽  
pp. 1168-1171
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Bird Species ◽  
Siamese Network ◽  
The Neural Network ◽  
Data Points ◽  
Bird Detection ◽  
Processing Techniques ◽  
Do So

The proposed system uses deep neural networks for identifying bird species. The model will be trained on bird images that are coming in the endangered species category. The application can also handle new data points, unlike existing systems that require model re-training for accommodating new data. The system can identify bird species in a large view of the image. The model will be trained using a convolutional neural network-based architecture called Siamese Network. This network is also called one-shot learning which means that it requires only few training example for each class. Existing models use image processing techniques or vanilla convolutional neural networks for classifying bird images. These models cannot accommodate new images and have to be retrained to do so. There is no commercially available system that can detect a species of bird in high resolution / large image. While in the Siamese network we only have to add new data, there is no need to retraining the neural network.

Object Tracking Using Improved Meanshift Algorithm Combined with Kalman Filter on Independent Visual Robotic Fish

2013 ◽  
Vol 333-335 ◽  
pp. 1030-1033
Author(s):  
Hai Hua Shi ◽  
Wei Xiang
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Target Tracking ◽  
Renewal Process ◽  
Robotic Fish ◽  
Moving Target ◽  
Complex Environment ◽  
Filter Model ◽  
Single Target ◽  
Single Target Tracking

This Paper Investigates an Improved Meanshift Algorithm Combined with Kalman Filter Aiming at Failure of a Target Tracking in Complex Environment for the Independent Visual Robotic Fish. First,we Need to Establish Kalman Filter Model of Moving Target. then,the Prediction and Renewal Process of Kalman Filter are Applied into the Meanshift Tracking Algorithm. Experimental Results Show that Improved Algorithm can Effectively Improve the Performance of Single Target Tracking in Complex Environment, and Realize Continuous Tracking of a Target. also, it can Obtain more Reliable Tracking Effect, and can be Used for more Complicated Scenes.

scholarly journals Towards real-time object detection on edge with deep neural networks

2018 ◽  
Author(s):  
◽  
Zhi Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Real Time ◽  
Real World ◽  
Deep Neural Networks ◽  
Learning Algorithm ◽  
Cloud Services ◽  
Training Data ◽  
Detection Model

Despite being a core topic for more than several decades, object detection is still receiving increasing attentions due to its irreplaceable importance in a wide variety of applications. Abundant object detectors based on deep neural networks have shown significantly revamped accuracies in recent years. However, it's still the day one for these models to be effectively deployed to real world. In this dissertation, we focus on object detection models which tackle real world problems that are unavailable few years ago. We also aim at making object detectors on the go, which means detectors are not longer required to be run on workstations and cloud services which is latency unfriendly. To achieve these goals, we addressed the problem in two phases: application and deployment. We have done thoughtful research on both areas. Our contribution involves inter-frame information fusing, model knowledge distillation, advanced model flow control for progressive inference, and hardware oriented model design and optimization. More specifically, we proposed a novel cross-frame verification scheme for spatial temporal fused object detection model for sequential images and videos in a proposal and reject favor. To compress model from a learning basis and resolve domain specific training data shortage, we improved the learning algorithm to handle insufficient labeled data by searching for optimal guidance paths from pre-trained models. To further reduce model inference cost, we designed a progressive neural network which run in flexible cost enabled by RNN style decision controller during runtime. We recognize the awkward model deployment problem, especially for object detection models that require excessive customized layers. In response, we propose to use end-to-end neural network which use pure neural network components to substitute traditional post-processing operations. We also applied operator decomposition and graph level and on-device optimization towards real-time object detection on low power edge devices. All these works have achieved state-of-the-art performances and converted to successful applications.

scholarly journals Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Florian Stelzer ◽  
André Röhm ◽  
Raul Vicente ◽  
Ingo Fischer ◽  
Serhiy Yanchuk
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Network ◽  
Single Neuron ◽  
Deep Neural Networks ◽  
Back Propagation ◽  
Local Network ◽  
Multiple Time ◽  
Learning Tools ◽  
Back Propagation Algorithm

AbstractDeep neural networks are among the most widely applied machine learning tools showing outstanding performance in a broad range of tasks. We present a method for folding a deep neural network of arbitrary size into a single neuron with multiple time-delayed feedback loops. This single-neuron deep neural network comprises only a single nonlinearity and appropriately adjusted modulations of the feedback signals. The network states emerge in time as a temporal unfolding of the neuron’s dynamics. By adjusting the feedback-modulation within the loops, we adapt the network’s connection weights. These connection weights are determined via a back-propagation algorithm, where both the delay-induced and local network connections must be taken into account. Our approach can fully represent standard Deep Neural Networks (DNN), encompasses sparse DNNs, and extends the DNN concept toward dynamical systems implementations. The new method, which we call Folded-in-time DNN (Fit-DNN), exhibits promising performance in a set of benchmark tasks.

Location- and Person-Independent Activity Recognition with WiFi, Deep Neural Networks, and Reinforcement Learning

2021 ◽  
Vol 2 (1) ◽  
pp. 1-25
Author(s):  
Yongsen Ma ◽  
Sheheryar Arshad ◽  
Swetha Muniraju ◽  
Eric Torkildson ◽  
Enrico Rantala ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reinforcement Learning ◽  
Activity Recognition ◽  
Deep Neural Networks ◽  
State Machine ◽  
Recognition Algorithm ◽  
The State ◽  
Neural Architecture ◽  
Learning Agent

In recent years, Channel State Information (CSI) measured by WiFi is widely used for human activity recognition. In this article, we propose a deep learning design for location- and person-independent activity recognition with WiFi. The proposed design consists of three Deep Neural Networks (DNNs): a 2D Convolutional Neural Network (CNN) as the recognition algorithm, a 1D CNN as the state machine, and a reinforcement learning agent for neural architecture search. The recognition algorithm learns location- and person-independent features from different perspectives of CSI data. The state machine learns temporal dependency information from history classification results. The reinforcement learning agent optimizes the neural architecture of the recognition algorithm using a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The proposed design is evaluated in a lab environment with different WiFi device locations, antenna orientations, sitting/standing/walking locations/orientations, and multiple persons. The proposed design has 97% average accuracy when testing devices and persons are not seen during training. The proposed design is also evaluated by two public datasets with accuracy of 80% and 83%. The proposed design needs very little human efforts for ground truth labeling, feature engineering, signal processing, and tuning of learning parameters and hyperparameters.

scholarly journals An efficient pruning scheme of deep neural networks for Internet of Things applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chen Qi ◽  
Shibo Shen ◽  
Rongpeng Li ◽  
Zhifeng Zhao ◽  
Qing Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Internet Of Things ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Compact Structure ◽  
Resource Limited ◽  
Benchmark Datasets ◽  
Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

Sign in / Sign up

Export Citation Format

Share Document