A parallel approach of multi-level morphological active contour algorithm for individual tree detection and crown delineation

Abstract

Forests in Taiwan contain a diverse variety. Remote sensing data could offer information of large area sampling, but it is very challenging to automatically detect tree and delineate three crown in remote sensing data. Recently a algorithm, called multi-level morphological active contour algorithm (MMAC), has been proposed to address these issues in [1]. It combines a multi-level morphological approach with the active contour model. However, this algorithm comes with a price, which is huge computational complexity, to prevent it from being implemented practically in medium-or largescale images. This manuscript aimed to accelerate MMAC by developing a parallel processing approach using reconfigurable computing platform with field-programmable gate arrays (FPGA). The experimental evaluation indicated that the proposed architecture could provide around 40% acceleration with simple implementation in hardware.Index Terms-Morphological active contour algorithm (MMAC); parallel processing; field programmable gate arrays (FPGA)

A Real-Time Tree Crown Detection Approach for Large-Scale Remote Sensing Images on FPGAs

“…Owing to above reasons, FPGA-based platforms have been broadly used for accelerating many on-board data processing tasks, including hyperspectral image processing (e.g., classification, anomaly detection, unmixing, etc.) [28,29], cloud detection [30], vehicle detection [31], tree crown detection [32], etc.…”

“…However, the high power consumption of GPU makes it difficult to satisfy the limited power budget of satellites for on-board data processing [26]. Chen et al [32] developed a parallel processing approach of the multi-level morphological active contour algorithm for tree crown detection on FPGA. The experimental results indicate that the proposed architecture could provide around 31% acceleration for an image with only 454 × 424 pixels compared with the simple implementation in Matlab.…”