Vision-Based Target Detection and Localization via a Team of Cooperative UAV and UGVs

Minaeian, Sara; Liu, Jian; Son, Young-Jun

doi:10.1109/tsmc.2015.2491878

Cited by 256 publications

(107 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where x is the input vector and x ∈ [0, 1], while w = {w (1) , w (2) } and b = {b (1) , b (2) } represent the weights and the biases of both layers. If the number of the hidden layer nodes is S 2 , we have…”

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

“…where b (2) ∈ n , z (3) ∈ n , W (2) ∈ n×s 2 , and a (3) ∈ n . The average of feedback error is used as the cost function…”

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

“…To do this, we train the first layer on raw inputs to obtain parameters W (1,1) , W (1,2) , b (1,1) , b (1,2) , then use the first layer to transform the raw input into a vector consisting of activation of the hidden units. The second layer is trained on this vector to obtain parameters W (2,1) , W (2,2) , b (2,1) , b (2,2) .…”

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

“…The second layer is trained on this vector to obtain parameters W (2,1) , W (2,2) , b (2,1) , b (2,2) . Repeatedly, we use the output of the previous layer as input for the subsequent layer.…”

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

“…The labels correspond to various estimated properties of an image and may be for example an object class label (road, car, sky, building, etc.) in the case of object class image segmentation [2]- [4].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Using Stacked Sparse Auto-Encoder and Superpixel CRF for Long-Term Visual Scene Understanding of UGVs

Qiu

Zhuang

et al. 2020

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Abstract-Multiple images have been widely used for scene understanding and navigation of unmanned ground vehicles in long term operations. However, as the amount of visual data in multiple images is huge, the cumulative error in many cases becomes untenable. This paper proposes a novel method that can extract features from a large dataset of multiple images efficiently. Then the membership K-means clustering is used for high dimensional features, and the large dataset is divided into N subdatasets to train N conditional random field (CRF) models based on superpixel. A Softmax subdataset selector is used to decide which one of the N CRF models is chosen as the prediction model for labeling images. Furthermore, some experiments are conducted to evaluate the feasibility and performance of the proposed approach.Index Terms-Conditional random field (CRF), long term navigation, scene understanding, stacked sparse auto-encoder.

show abstract

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

“…where b (2) ∈ n , z (3) ∈ n , W (2) ∈ n×s 2 , and a (3) ∈ n . The average of feedback error is used as the cost function…”

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

Section: Unsupervised Images Feature Learning With Stacked Sparsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Using Stacked Sparse Auto-Encoder and Superpixel CRF for Long-Term Visual Scene Understanding of UGVs

Qiu

Zhuang

et al. 2020

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

show abstract

Implementation of an efficient extreme learning machine for node localization in unmanned aerial vehicle assisted wireless sensor networks

Annepu

Anbazhagan

2019

Int J Communication

View full text Add to dashboard Cite

Accurate node localization in wireless sensor networks (WSNs) is an essential for many networking protocols like clustering, routing, and network map building. The classical localization techniques such as multilateration and optimization-based least square localization (OLSL) techniques estimate position of unknown node (UN) from the distance measured between all anchor nodes (ANs) and UNs. On the other hand, node localization using fixed terrestrial ANs suffers from poor localization accuracy because the ground to ground (GG) channel link is not reliable. By contrast, the mobile anchor deployed in unmanned aerial vehicle (UAV) provides high localization accuracy through reliable air to ground (AG) channel link. Still, the nonlinear distortion introduced in the wireless channel makes the distance measurement noisy. This noisy distance measurement also limits localization accuracy of classical localization techniques. Hence, the highly nonlinear artificial neural network (ANN) models such as multilayer perceptron (MLP) models can be applied effectively for node localization in UAV-assisted WSNs. However, the MLP suffers from slow training speed, which limits its usage in real-time applications.So, the extreme learning machine (ELM) is found to be a better alternative because it works on empirical error minimization theory, and its learning process requires only a single iteration. The detailed simulation analysis supports the proposed ELM localization scheme in terms of both localization accuracy and computational complexity.

show abstract

A compact W‐band quasi‐optical detector packaged by meta‐surface reflector and 3D‐printed lens

Qiao

Líu²,

Mou³

et al. 2019

Micro & Optical Tech Letters

View full text Add to dashboard Cite

This article presents a compact W‐band quasi‐optical detector that can be easily extended into an array for focal plane imaging applications. The quasi‐optical detector consists of an antenna‐coupled detector packaged by a low‐profile meta‐surface reflector and a 3D‐printed lens. The antenna‐coupled detector with a GaAs Schottky diode is printed on a low‐cost and low‐loss laminate. To extract the detected low‐frequency signal within a small footprint, a pair of vertical metallic posts instead of conventional planar strips is designed and loaded at the ends of the antenna. For facilitating unidirectional radiation patterns, a low‐profile meta‐surface reflector with a thickness of λg/8 is placed under the antenna‐coupled detector. In addition, a 3D‐printed dielectric lens is loaded upon the antenna‐coupled detector, which can enhance the radiation gain by 6 dB. Both the meta‐surface reflector and the 3D‐printed lens are fixed by an asymmetric H‐shaped framework, forming a low‐cost and lightweight package for the detector. Based on the proposed detector, a W‐band 1 × 16 array is experimentally demonstrated, exhibiting a responsivity of 100 V/W~410 V/W from 92 to 110 GHz. The total size of the array is only 27 λ × 4 λ × 1.8 λ, where λ is the free space wavelength at the center frequency.

show abstract

Vision-Based Target Detection and Localization via a Team of Cooperative UAV and UGVs

Cited by 256 publications

References 23 publications

Using Stacked Sparse Auto-Encoder and Superpixel CRF for Long-Term Visual Scene Understanding of UGVs

Using Stacked Sparse Auto-Encoder and Superpixel CRF for Long-Term Visual Scene Understanding of UGVs

Implementation of an efficient extreme learning machine for node localization in unmanned aerial vehicle assisted wireless sensor networks

A compact W‐band quasi‐optical detector packaged by meta‐surface reflector and 3D‐printed lens

Contact Info

Product

Resources

About