Hyperspectral image processing for target detection using Spectral Angle Mapping

Panda, Amrit; Pradhan, Debasish

doi:10.1109/iic.2015.7150911

Cited by 11 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, where L is the set of labels, I y,x is a spectral pixel at location y,x in the input, and C is the inferred class on that location in the HS cube. The label with the smallest angle to the reference sample is returned by Equation (5). We propose to translate the SAM algorithm into the CNN paradigm and refer to it as SAMNet.…”

Section: Samnetmentioning

confidence: 99%

“…The cos −1 operator of Equation ( 4) does not need to be included because is has no effect on the arg min operator in Equation ( 5). This CNN definition of the SAM algorithm provides more flexibility in terms of changing the footprint and training convolutional parameters 5 .…”

Section: Samnetmentioning

confidence: 99%

“…A traditional method of spectral analysis is using the linear methods to correlate the known spectra of a polymer with an unknown spectra, using for example Spectral Angle Mapping (SAM) [5]. However, a limitation of (linearly) classifying individual spectral pixels of images is the loss of context information.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the Effect of Pre-Processing and Model Complexity for Plastic Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging

Dijkstra¹,

Aghaei²,

Jaarsma³

et al. 2022

Preprint

View full text Add to dashboard Cite

The importance of plastic waste recycling is undeniable. In this respect, computer vision and deep learning enable solutions through the automated analysis of short-wave-infrared hyper-spectral images of plastics. In this paper, we offer an exhaustive empirical study to show the importance of efficient model selection for resolving the task of hyper-spectral image segmentation of various plastic flakes using deep learning. We assess the complexity level of generic and specialized models and infer their performance capacity: generic models are often unnecessarily complex. We introduce two variants of a specialized hyper-spectral architecture, PlasticNet, that outperforms several well-known segmentation architectures in both performance as well as computational complexity. In addition, we shed lights on the significance of signal pre-processing within the realm of hyper-spectral imaging. To complete our contribution, we introduce the largest, most versatile hyper-spectral dataset of plastic flakes of four primary polymer types.

show abstract

Section: Samnetmentioning

confidence: 99%

Section: Samnetmentioning

confidence: 99%

See 1 more Smart Citation

On the Effect of Pre-Processing and Model Complexity for Plastic Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging

Dijkstra¹,

Aghaei²,

Jaarsma³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The detection accuracy can be evaluated via spectral angle mapper (SAM) [47] values (in degrees) between the detected target and the reference spectral signature, which reflects the similarity of pixels in an HSI. The SAM between two pixel vectors x i and x j is defined by the following expressions,…”

Section: Analysis Of Target Detection Accuracymentioning

confidence: 99%

A Novel FPGA-Based Architecture for Fast Automatic Target Detection in Hyperspectral Images

Lei

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Onboard target detection of hyperspectral imagery (HSI), considered as a significant remote sensing application, has gained increasing attention in the latest years. It usually requires processing huge volumes of HSI data in real-time under constraints of low computational complexity and high detection accuracy. Automatic target generation process based on an orthogonal subspace projector (ATGP-OSP) is a well-known automatic target detection algorithm, which is widely used owing to its competitive performance. However, ATGP-OSP has an issue to be deployed onboard in real-time target detection due to its iteratively calculating the inversion of growing matrices and increasing matrix multiplications. To resolve this dilemma, we propose a novel fast implementation of ATGP (Fast-ATGP) while maintaining target detection accuracy of ATGP-OSP. Fast-ATGP takes advantage of simple regular matrix add/multiply operations instead of increasingly complicated matrix inversions to update growing orthogonal projection operator matrices. Furthermore, the updated orthogonal projection operator matrix is replaced by a normalized vector to perform the inner-product operations with each pixel for finding a target per iteration. With these two major optimizations, the computational complexity of ATGP-OSP is substantially reduced. What is more, an FPGA-based implementation of the proposed Fast-ATGP using high-level synthesis (HLS) is developed. Specifically, an efficient architecture containing a bunch of pipelines being executed in parallel is further designed and evaluated on a Xilinx XC7VX690T FPGA. The experimental results demonstrate that our proposed FPGA-based Fast-ATGP is able to automatically detect multiple targets on a commonly used dataset (AVIRIS Cuprite Data) at a high-speed rate of 200 MHz with a significant speedup of nearly 34.3 times that of ATGP-OSP, while retaining nearly the same high detection accuracy. data analysis, it is rather rare and may be difficult to find because many of HSI-detected targets are relatively small and weak, such as anomalies [10]. Consequently, real-time target detection in HSI presents a great challenge and has become increasingly important.Currently, many algorithms have been developed for target detection in HSI, such as unsupervised fully constrained least squares (UFCLS) [11], automatic target-generation process based on an orthogonal subspace projector (ATGP-OSP) [12], and Reed-Xiaoli (RX) detector [13]. Among them, the performance of ATGP performs well in terms of detection accuracy and computational complexity according to the quantitative and comparative assessments [14,15]. However, despite the fact that automatic target detection has received increasing attention [16][17][18], two problems with real-time onboard applications need to be addressed. One is to continuously increase the scale of operations in the process of automatically iterating to update currently being found targets, which complicates the process of updating operator matrix. The other one is a large-scale matrix m...

show abstract

“…Classical classification technique such as spectral angle mapping is taken advantage of for target detection [12]. To further cut down the calculation cost, user-defined camouflage evaluation index is attempted to realize camouflage target detection [13].…”

Section: Introductionmentioning

confidence: 99%

Research on Camouflage Target Detection via Computational Analysis with Spectral Imaging

Chen¹,

Zhou²,

Chen³

et al. 2018

dtcse

View full text Add to dashboard Cite

Camouflage target detection is one of most important techniques in a great number of applications such as remote sensing, security monitoring and industrial production. In this paper, high-resolution spectral imaging together with computational analysis on spectral data cube is adopted to solve camouflage target recognition problem. Spectral data cubes of certain experimental scene are collected by a self-developed visual-band imaging spectrometer, and spectral information divergence (SID) is adopted as difference descriptor to discriminate abnormal target. SIDs of the whole spectral region and several specific ranges are all measured to quantitatively evaluate the effort of band selection on camouflage detection. This is proven to be a low-cost and effective tool for camouflage target detection and can be further developed beyond visual band spectral imaging technique.

show abstract

Hyperspectral image processing for target detection using Spectral Angle Mapping

Cited by 11 publications

References 4 publications

On the Effect of Pre-Processing and Model Complexity for Plastic Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging

On the Effect of Pre-Processing and Model Complexity for Plastic Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging

A Novel FPGA-Based Architecture for Fast Automatic Target Detection in Hyperspectral Images

Research on Camouflage Target Detection via Computational Analysis with Spectral Imaging

Contact Info

Product

Resources

About