《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 嵌入式技术 > 设计应用 > 基于非对称编码的无人机巡检图像压缩方法
基于非对称编码的无人机巡检图像压缩方法
电子技术应用
辛帅魁,吴明慧,戚满顺,秦齐,程嘉诚,朱天昊
1.国网江苏省电力有限公司南京市江北新区供电分公司;2.国网江苏省电力有限公司南京供电分公司
摘要: 随着无人机技术在电网运检中的广泛应用,图像压缩传输技术日趋重要。为解决无人机图像处理算力不足,巡检图像压缩耗时长、效果差的问题,提出了一种基于非对称编码的无人机巡检图像压缩方法。首先,通过去除图像冗余空间、图像色彩量化有效地提高了无人机巡检图像压缩率;其次,通过压缩模型轻量化适配,降低线路巡检图像压缩算力要求;在此基础上,通过高质量的图像恢复增强,提高了图像的峰值信噪比。最后,该方法在某省电力科学研究院中进行了仿真应用,其恢复图像峰值信噪比为34.2 dB,平均压缩与恢复时间为4 632 ms。所提方法能有效提高无人机巡检图像压缩速度,提高恢复图像质量。
中圖分類號:TH89 文獻標志碼:A DOI: 10.16157/j.issn.0258-7998.256850
中文引用格式: 辛帥魁,吳明慧,戚滿順,等. 基于非對稱編碼的無人機巡檢圖像壓縮方法[J]. 電子技術(shù)應(yīng)用,2026,52(2):57-61.
英文引用格式: Xin Shuaikui,Wu Minghui,Qi Manshun,et al. Unmanned aerial vehicle inspection image compression method based on asymmetric coding[J]. Application of Electronic Technique,2026,52(2):57-61.
Unmanned aerial vehicle inspection image compression method based on asymmetric coding
Xin Shuaikui1,Wu Minghui2,Qi Manshun2,Qin Qi1,Cheng Jiacheng2,Zhu Tianhao2
1.State Grid Nanjing City Jiangbei District Electric Power Supply Company;2.State Grid Nanjing Power Supply Company
Abstract: With the widespread application of drone technology in power grid operation and inspection, image compression transmission technology is becoming increasingly important. To solve the problems of insufficient computing power in drone image processing, long compression time and poor performance of inspection images, a drone inspection image compression method based on asymmetric encoding is proposed. Firstly, by removing redundant image space and quantifying image colors, the compression rate of drone inspection images has been effectively improved. Secondly, by compressing the model and adapting it with lightweight design, the computational requirements for compressing inspection images of power lines can be reduced. On this basis, the peak signal-to-noise ratio of the image was improved through high-quality image restoration enhancement. Finally, the method proposed in this paper was simulated and applied in a certain provincial electric power science research institute, with a peak signal-to-noise ratio of 34.2 dB and an average compression and recovery time of 4 632 ms. The proposed method can effectively improve the compression speed of unmanned aerial vehicle inspection images and enhance the quality of restored images.
Key words : asymmetric coding;drone inspection;image compression;image color quantization;peak signal-to-noise ratio

引言

隨著電網(wǎng)數(shù)字化建設(shè)工作的不斷開展,無人機技術(shù)在電網(wǎng)運檢中得到了廣泛的應(yīng)用[1-2]。當前用于電網(wǎng)運檢的無人機裝備不斷增多,無人機自主電網(wǎng)巡檢技術(shù)已初具規(guī)模[3]。但無人機巡檢時產(chǎn)生的大量級影像數(shù)據(jù),造成數(shù)據(jù)通信費用高、存儲設(shè)備投資大的問題[4-5]。因此,探索無人機拍攝的電網(wǎng)巡檢圖片進行有效壓縮,對無人機巡檢具有積極的意義。

國內(nèi)外許多學(xué)者對無人機巡檢圖像壓縮方法做了大量研究。文獻[6]中提出了一種基于圖像語義編碼的無人機巡檢圖像壓縮方法,對圖像進行語義提取,并進行編碼和傳輸,提高了圖像壓縮率。文獻[7]中通過雙錐特征融合圖像壓縮方法對無人機巡檢圖像進行壓縮,以提高圖像壓縮率。文獻[8]中提出了一種基于殘差特征聚合的圖像壓縮方法,通過重構(gòu)子網(wǎng)絡(luò)壓縮無人機圖像。文獻[9]中提出了一種自適應(yīng)加權(quán)的圖像壓縮方法,采用K奇異值分解對無人機巡檢圖像進行壓縮。由此可見,無人機圖像壓縮方法多樣,且取得了一定的成果。但上述方法對無人機圖形處理器性能要求較高,現(xiàn)有無人機圖像處理算力不足,造成圖像壓縮耗時長,圖像壓縮效果差,不能滿足電力缺陷識別的要求。

為解決無人機圖像處理算力不足,電網(wǎng)巡檢圖像壓縮耗時長、效果差的問題,提出了一種基于非對稱編碼的無人機巡檢圖像壓縮方法。通過非對稱編解碼圖像壓縮技術(shù)對神經(jīng)網(wǎng)絡(luò)的輸入、隱含層網(wǎng)絡(luò)進行拆分,建立輕量化神經(jīng)網(wǎng)絡(luò)模型,降低了無人機處理電網(wǎng)巡檢圖像的算力;通過輸出層實現(xiàn)無人機電網(wǎng)巡檢圖像的增強恢復(fù)解碼,滿足電網(wǎng)巡檢圖像識別要求。


本文詳細內(nèi)容請下載:

http://ihrv.cn/resource/share/2000006970


作者信息:

辛帥魁1,吳明慧2,戚滿順2,秦齊1,程嘉誠2,朱天昊2

(1.國網(wǎng)江蘇省電力有限公司南京市江北新區(qū)供電分公司,江蘇 南京 211899;

2.國網(wǎng)江蘇省電力有限公司南京供電分公司,江蘇 南京 210019)

2.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。