A deep pipelined implementation of hyperspectral target detection algorithm on FPGA using HLS

Jie Lei, Yunsong Li, Dongsheng Zhao, Jing Xie, Chein I. Chang, Lingyun Wu, Xuepeng Li, Jintao Zhang, Wenguang Li

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)


Real-time target detection for hyperspectral images (HSI) has received considerable interest in recent years. However, owing to enormous data volume provided by HSI, detection algorithms are generally computationally complex, thus developing rapid processing techniques for target detection has encountered several challenging issues. It seems that using a deep pipelined structure can improve the detection speed, and implementing on field programmable gate arrays (FPGAs) can also achieve concurrent operations rather than run streams of sequential instruction. This paper presents a deep pipelined background statistics (DPBS) approach to optimizing and implementing a well-known subpixel target detection algorithm, called constrained energy minimization (CEM) on FPGA by using high-level synthesis (HLS). This approach offers significant benefits in terms of increasing data throughput and improving design efficiency. To overcome a drawback of HLS on implementing a task-level pipelined circuit that includes a feedback data path, a script based circuit design method is further developed to make connections between some of the modules created by HLS. Experimental results show that the proposed method can detect targets on a real-hyperspectral data set (HyMap Data) only in 0.15 s without compromising detection accuracy.

Original languageEnglish
Article number516
JournalRemote Sensing
Issue number4
Publication statusPublished - 2018 Apr 1

All Science Journal Classification (ASJC) codes

  • General Earth and Planetary Sciences


Dive into the research topics of 'A deep pipelined implementation of hyperspectral target detection algorithm on FPGA using HLS'. Together they form a unique fingerprint.

Cite this