scholarly journals UAV Object Tracking Application Based on Patch Color Group Feature on Embedded System

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1864
Author(s):  
Ming-Hwa Sheu ◽  
Yu-Syuan Jhang ◽  
S M Salahuddin Morsalin ◽  
Yao-Fong Huang ◽  
Chi-Chia Sun ◽  
...  
Keyword(s):  
Computational Complexity ◽  
Embedded System ◽  
Object Tracking ◽  
Tracking System ◽  
Computational Cost ◽  
Gaussian Mixture ◽  
Raspberry Pi ◽  
Color Group ◽  
Current Frame ◽  
Low Computational Complexity

The discriminative object tracking system for unmanned aerial vehicles (UAVs) is widely used in numerous applications. While an ample amount of research has been carried out in this domain, implementing a low computational cost algorithm on a UAV onboard embedded system is still challenging. To address this issue, we propose a low computational complexity discriminative object tracking system for UAVs approach using the patch color group feature (PCGF) framework in this work. The tracking object is separated into several non-overlapping local image patches then the features are extracted into the PCGFs, which consist of the Gaussian mixture model (GMM). The object location is calculated by the similar PCGFs comparison from the previous frame and current frame. The background PCGFs of the object are removed by four directions feature scanning and dynamic threshold comparison, which improve the performance accuracy. In the terms of speed execution, the proposed algorithm accomplished 32.5 frames per second (FPS) on the x64 CPU platform without a GPU accelerator and 17 FPS in Raspberry Pi 4. Therefore, this work could be considered as a good solution for achieving a low computational complexity PCGF algorithm on a UAV onboard embedded system to improve flight times.

scholarly journals Fast and Economical Object Tracking using Raspberry Pi 3.0

2019 ◽  
Vol 8 (6S) ◽  
pp. 336-338
Keyword(s):  
Computer Vision ◽  
Power Consumption ◽  
Low Power ◽  
Object Detection ◽  
Object Tracking ◽  
Tracking System ◽  
Low Power Consumption ◽  
Raspberry Pi ◽  
Multiple Object Detection ◽  
Vision Application

This paper proposes a way to construct a financially cheap and fast object tracking using Raspberry Pi3. Multiple object detection is an important step in any computer vision application. Since the number of cameras included is more these gadgets are compelled by expense per hub, control utilization and handling power. We propose a tracking system with low power consumption. The framework is completely designed with python and OpenCV. The tracking quality and accuracy is measured using publicly available datasets.

scholarly journals Development of a Portable, Reliable and Low-Cost Electrical Impedance Tomography System Using an Embedded System

Electronics ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 15
Author(s):  
Francisco Zamora-Arellano ◽  
Oscar Roberto López-Bonilla ◽  
Enrique Efrén García-Guerrero ◽  
Jesús Everardo Olguín-Tiznado ◽  
Everardo Inzunza-González ◽  
...  
Keyword(s):  
Image Reconstruction ◽  
Embedded System ◽  
Electrical Impedance Tomography ◽  
Food Industry ◽  
Electrical Impedance ◽  
Low Cost ◽  
Computational Cost ◽  
Raspberry Pi ◽  
Impedance Tomography ◽  
The Real

Electrical impedance tomography (EIT) is a useful procedure with applications in industry and medicine, particularly in the lungs and brain area. In this paper, the development of a portable, reliable and low-cost EIT system for image reconstruction by using an embedded system (ES) is introduced herein. The novelty of this article is the hardware development of a complete low-cost EIT system, as well as three simple and efficient algorithms that can be implemented on ES. The proposed EIT system applies the adjacent voltage method, starting with an impedance acquisition stage that sends data to a Raspberry Pi 4 (RPi4) as ES. To perform the image reconstruction, a user interface was developed by using GNU Octave for RPi4 and the EIDORS library. A statistical analysis is performed to determine the best average value from the samples measured by using an analog-to-digital converter (ADC) with a capacity of 30 kSPS and 24-bit resolution. The tests for the proposed EIT system were performed using materials such as metal, glass and an orange to simulate its application in food industry. Experimental results show that the statistical median is more accurate with respect to the real voltage measurement; however, it represents a higher computational cost. Therefore, the mean is calculated and improved by discarding data values in a transitory state, achieving better accuracy than the median to determine the real voltage value, enhancing the quality of the reconstructed images. A performance comparison between a personal computer (PC) and RPi4 is presented. The proposed EIT system offers an excellent cost-benefit ratio with respect to a traditional PC, taking into account precision, accuracy, energy consumption, price, light weight, size, portability and reliability. The proposed EIT system has potential application in mechanical ventilation, food industry and structural health monitoring.

scholarly journals Measure of Similarity between GMMs by Embedding of the Parameter Space That Preserves KL Divergence

Mathematics ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 957
Author(s):  
Branislav Popović ◽  
Lenka Cepova ◽  
Robert Cep ◽  
Marko Janev ◽  
Lidija Krstanović
Keyword(s):  
Computational Complexity ◽  
Parameter Space ◽  
Recognition Accuracy ◽  
Gaussian Mixture Models ◽  
Gaussian Mixture ◽  
Dimensional Manifold ◽  
Dimensional Parameter ◽  
Trade Off ◽  
Measure Of Similarity ◽  
Lower Dimensional

In this work, we deliver a novel measure of similarity between Gaussian mixture models (GMMs) by neighborhood preserving embedding (NPE) of the parameter space, that projects components of GMMs, which by our assumption lie close to lower dimensional manifold. By doing so, we obtain a transformation from the original high-dimensional parameter space, into a much lower-dimensional resulting parameter space. Therefore, resolving the distance between two GMMs is reduced to (taking the account of the corresponding weights) calculating the distance between sets of lower-dimensional Euclidean vectors. Much better trade-off between the recognition accuracy and the computational complexity is achieved in comparison to measures utilizing distances between Gaussian components evaluated in the original parameter space. The proposed measure is much more efficient in machine learning tasks that operate on large data sets, as in such tasks, the required number of overall Gaussian components is always large. Artificial, as well as real-world experiments are conducted, showing much better trade-off between recognition accuracy and computational complexity of the proposed measure, in comparison to all baseline measures of similarity between GMMs tested in this paper.

scholarly journals Air Learning: a deep reinforcement learning gym for autonomous aerial robot visual navigation

2021 ◽  
Author(s):  
Srivatsan Krishnan ◽  
Behzad Boroujerdian ◽  
William Fu ◽  
Aleksandra Faust ◽  
Vijay Janapa Reddi
Keyword(s):  
Reinforcement Learning ◽  
Embedded System ◽  
Broad Class ◽  
Visual Navigation ◽  
Raspberry Pi ◽  
Latency Distribution ◽  
Hardware In The Loop ◽  
Resource Constrained ◽  
Aerial Robot ◽  
Policy Optimization

AbstractWe introduce Air Learning, an open-source simulator, and a gym environment for deep reinforcement learning research on resource-constrained aerial robots. Equipped with domain randomization, Air Learning exposes a UAV agent to a diverse set of challenging scenarios. We seed the toolset with point-to-point obstacle avoidance tasks in three different environments and Deep Q Networks (DQN) and Proximal Policy Optimization (PPO) trainers. Air Learning assesses the policies’ performance under various quality-of-flight (QoF) metrics, such as the energy consumed, endurance, and the average trajectory length, on resource-constrained embedded platforms like a Raspberry Pi. We find that the trajectories on an embedded Ras-Pi are vastly different from those predicted on a high-end desktop system, resulting in up to $$40\%$$ 40 % longer trajectories in one of the environments. To understand the source of such discrepancies, we use Air Learning to artificially degrade high-end desktop performance to mimic what happens on a low-end embedded system. We then propose a mitigation technique that uses the hardware-in-the-loop to determine the latency distribution of running the policy on the target platform (onboard compute on aerial robot). A randomly sampled latency from the latency distribution is then added as an artificial delay within the training loop. Training the policy with artificial delays allows us to minimize the hardware gap (discrepancy in the flight time metric reduced from 37.73% to 0.5%). Thus, Air Learning with hardware-in-the-loop characterizes those differences and exposes how the onboard compute’s choice affects the aerial robot’s performance. We also conduct reliability studies to assess the effect of sensor failures on the learned policies. All put together, Air Learning enables a broad class of deep RL research on UAVs. The source code is available at: https://github.com/harvard-edge/AirLearning.

scholarly journals Non-parallel dictionary learning for voice conversion using non-negative Tucker decomposition

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Yuki Takashima ◽  
Toru Nakashika ◽  
Tetsuya Takiguchi ◽  
Yasuo Ariki
Keyword(s):  
Dictionary Learning ◽  
Computational Cost ◽  
Tensor Decomposition ◽  
Gaussian Mixture ◽  
Voice Conversion ◽  
Specific Information ◽  
Learning Method ◽  
Tucker Decomposition ◽  
Parallel Data ◽  
High Computational Cost

Abstract Voice conversion (VC) is a technique of exclusively converting speaker-specific information in the source speech while preserving the associated phonemic information. Non-negative matrix factorization (NMF)-based VC has been widely researched because of the natural-sounding voice it achieves when compared with conventional Gaussian mixture model-based VC. In conventional NMF-VC, models are trained using parallel data which results in the speech data requiring elaborate pre-processing to generate parallel data. NMF-VC also tends to be an extensive model as this method has several parallel exemplars for the dictionary matrix, leading to a high computational cost. In this study, an innovative parallel dictionary-learning method using non-negative Tucker decomposition (NTD) is proposed. The proposed method uses tensor decomposition and decomposes an input observation into a set of mode matrices and one core tensor. The proposed NTD-based dictionary-learning method estimates the dictionary matrix for NMF-VC without using parallel data. The experimental results show that the proposed method outperforms other methods in both parallel and non-parallel settings.

Sign in / Sign up

Export Citation Format

Share Document