FPGA implementation of collaborative representation algorithm for real-time hyperspectral target detection

Wu, Jingjing; Jin, Yu; Li, Wei; Gao, Lianru; Zhang, Bing

doi:10.1007/s11554-018-0823-7

Cited by 8 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysing the state-of-the-art architectures, we can observe that, like our proposal, [47] and [48] use fixed-point precision instead of floating-point notation, because this arithmetic is more suitable for FPGA technology providing better results. By contrary, [49] adopts floating-point arithmetic, whose performance is the worst of the evaluated proposals.…”

Section: Discussionmentioning

confidence: 85%

“…In [47], the RX algorithm, optimized by a streaming background statistics approach, has been developed in a Kintex-7 XC7K325T FPGA (KC705 Evaluation Kit). Another interesting anomaly detection algorithm is the Collaborative-Representation-Based Detector (CRD), which has been implemented on a Virtex-7 XC7VX980T FPGA in [48]. Finally, the anomaly detector presented in [49] is based on morphological reconstruction and a simplified guided filter (Fast-MGD) that has been implemented on a Virtex-7 XC7VX690T.…”

Section: Discussionmentioning

confidence: 99%

“…It is worth mentioning that the proposed architecture has a better time performance than the other proposals; the HW-LbL-FAD detector processes five and seven times more data than the second better proposal ( [47]) in its slowest (100MHz) and fastest (143MHz) versions, respectively. Although proposals presented in [48] and [49] employ tiny hypersepectral cubes, both achieve worse time-performance balance. From the point of view of hardware utilization in terms of FPGA technology, Table V shows the hardware utilization by each anomaly detector in number of resources an its percentage according to the device and the data set.…”

Section: Discussionmentioning

confidence: 99%

“…Table IV displays the price of each FPGA device and the summary of the number of available hardware resources. The architectures based on Virtex-7 devices, [48] and [49], have a high economic cost that may be unaffordable for embedded systems, whilst the one based on a Kintex-7 device has a better price but its performance is so far to process large hyperspectral cubes. However, our proposal is a low-cost solution that exploits the FPGA technology as much as possible, obtaining the best trade-off between performance and cost.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Low-Power Hyperspectral Anomaly Detector Implementation in Cost-Optimized FPGA Devices

Caba

Díaz²,

Barba

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Onboard data processing for on-the-fly decisionmaking applications has recently gained momentum in the field of remote sensing. In this context, hyperspectral anomaly detection has received a special attention since its main purpose lays on the identification of abnormal events in an unsupervised manner. Nevertheless, onboard real-time hyperspectral image processing still poses several challenges before becoming a reality. This is why there is an emerging trend towards the development of hardware-friendly algorithmic solutions embedded in reconfigurable devices. In this context, this work contributes with a hardware architecture that ensures a progressive line processing in time-sensitive applications limited by the scarcity of hardware resources. In this sense, we have implemented the state-of-theart HW-LbL-FAD detector on a reconfigurable hardware for a real-time performance. Specifically, we have selected a costoptimized FPGA (ZC7Z020-CLG484) to implement our solution whose results draw up a good trade-off between the following three features: time performance, energy consumption and cost. The experimental results indicate our hardware component is able to process hyperspectral images of 825x1024 pixels and 160 bands in 0.51 seconds with a power-budget of 1.3 watts and a device cost around 150 C. Regarding detection performance, the HW-LbL-FAD algorithm outperforms other state-of-the-art algorithms.

show abstract

Section: Discussionmentioning

confidence: 85%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Low-Power Hyperspectral Anomaly Detector Implementation in Cost-Optimized FPGA Devices

Caba

Díaz²,

Barba

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The sixteenth paper entitled "FPGA implementation of collaborative representation algorithm for real-time hyperspectral target detection" by Wu et al [16] presents a novel FPGA-based technique for efficient real-time target detection in hyperspectral images. The collaborative representation based target detection (CRD) algorithm is employed.…”

Section: Real-time Image Processingmentioning

confidence: 99%