[Objective] The aim of this study was to improve the cotton image segmentation accuracy in a picking robot image processing system. [Method] An image segmentation algorithm based on a fusion method of Markov random field and quantum particle swarm optimization clustering was proposed. The process of the proposed algorithm is as follows: first, transform the RGB (red, green, blue) images into grayscale; second, use it to segment these images; finally, the threshold of the connected area is set on the basis of the segmented image to obtain the target area. Then, the cotton front image and the cotton side image are selected from the images collected from different angles. The segmentation experiment was carried out by using this algorithm, and compared with the Otsu algorithm, the fuzzy C-means algorithm, the quantum particle swarm image segmentation algorithm and the Markov random field image segmentation algorithm. [Result] The results showed that the segmentation accuracy and peak signal to noise ratio of the proposed algorithm were 98.94% and 77.48 dB. When compared with the Otsu algorithm, fuzzy C-means algorithm, quantum particle swarm optimization algorithm and Markov random field algorithm, the average segmentation accuracy and peak signal to noise ratio of the proposed algorithm increased by 2.47%–4.56%, and 9.81–13.11 dB, respectively. [Conclusion] The proposed algorithm had higher segmentation accuracy and higher peak signal to noise ratio than the other algorithms tested. 相似文献
Lack of quantitative observations of extent, frequency, and severity of large historical fires constrains awareness of departure of contemporary conditions from those that demonstrated resistance and resilience to frequent fire and recurring drought.
Objectives
Compare historical and contemporary fire and forest conditions for a dry forest landscape with few barriers to fire spread.
Methods
Quantify differences in (1) historical (1700–1918) and contemporary (1985–2015) fire extent, fire rotation, and stand-replacing fire and (2) historical (1914–1924) and contemporary (2012) forest structure and composition. Data include 85,750-ha tree-ring reconstruction of fire frequency and extent; >?375,000-ha timber inventory following >?78,900-ha fires in 1918; and remotely-sensed maps of contemporary fire effects and forest conditions.
Results
Historically, fires?>?20,000 ha occurred every 9.5 years; fire rotation was 14.9 years; seven fires?>?40,469 ha occurred during extreme drought (PDSI <?? 4.0); and stand-replacing fire occurred primarily in lodgepole (Pinus contorta var. murrayana). In contemporary fires, only 5% of the ecoregion burned in 30 years, and stand-replacing fire occurred primarily in ponderosa (Pinus ponderosa) and mixed-conifer. Historically, density of conifers?>?15 cm dbh exceeded 120 trees/ha on?<?5% of the area compared to 95% currently.
Conclusions
Frequent, large, low-severity fires historically maintained open-canopy ponderosa and mixed-conifer forests in which large fire- and drought-tolerant trees were prevalent. Stand-replacing patches in ponderosa and mixed-conifer were rare, even in fires >?40,469 ha (minimum size of contemporary “megafires”) during extreme drought. In this frequent-fire landscape, mixed-severity fire historically influenced lodgepole and adjacent forests. Lack of large, frequent, low-severity fires degrades contemporary forest ecosystems.