An edge detection technique has been proposed to facilitate the automatic alignment of boarding bridges with aircraft doors, thereby addressing issues associated with manual operation and potential collisions during the conventional docking process. To enhance the robustness of noise suppression, pixel value difference-based weights have been introduced as weighting factors in the median filtering process, wherein pixels assigned higher weights exert a greater influence on the median calculation. Threshold segmentation has been performed using Otsu’s method based on maximum inter-class variance, enabling the automatic determination of an optimal threshold and thereby improving the accuracy of aircraft door feature extraction. Furthermore, the Sobel operator has been modified by integrating a weighted average of neighboring pixel values, which significantly enhances its edge detection performance. Experimental results have demonstrated that the application of weighted median filtering improves the peak signal-to-noise ratio (PSNR) of the image to 37.93 dB, representing a 13.95% increase compared to conventional median filtering. The modified Sobel operator has been shown to increase the number of detected edge points by 134.5% relative to other operators, with improvements of 25.2% in precision, 193.6% in recall, and 136.1% in the F1 score. These results provide meaningful insights into the optimization of edge detection methodologies for aircraft door localization.
LIN Bin-bin, LI Yi-ke, ZHANG Heng-ming.
Aircraft Cabin Door Edge Detection Based on Weighted Approach[J].
Science Technology and Engineering, 2026, 26(9): 3885-3894 DOI:10.12404/j.issn.1671-1815.2502540
为了评估不同阈值分割处理的效果,引入了Dice系数和交并比(intersection over union, IoU)作为评估指标用来衡量分割结果与真实标注之间的相似性,其中真实标注是人为手动创建,更真实可靠。Dice系数衡量的是两个集合的相似度,取值范围为0~1,值越高表示分割结果与真实标注的重叠程度越高,IoU则表示预测区域和真实区域的重叠程度,同样取值范围为0~1,值越高表示分割结果越准确。
ZhangJian, YangHao. Research and application of measurement technology for large aircraft door parts[C]// Proceedings of the 10th Youth Science and Technology Forum of the Chinese Society of Aeronautics and Astronautics. Nanchang: Quality Department, Chinese Society of Aeronautics and Astronautics, 2022: 232-235.
YeRun, ZhangCheng, LiXu, et al. Research on recognition and positioning technology of passenger aircraft door based on computer vision[J]. Computer Measurement and Control, 2021, 29(3): 224-229.
ZhangChangyong, GuoCong, LiYuzhou, et al. Research on identification and positioning method for aircraft door based on improved YOLOv5[J]. Computer Measurement and Control, 2024, 32(1): 142-149.
ZhaoHongwei, HuPengyu, YangShuming, et al. Measurement technology and its application of aircraft door gap based on surface structured light[J]. Science Technology and Engineering, 2024, 24(3): 1045-1051.
HuShan. Discussion on image denoising technology based on improved adaptive weighted mean filtering[J]. Journal of Puer University, 2022, 38(6): 41-43.
ZhangQiaoling, MaZiping, XueRuizhi. Research and analysis of several image denoising methods based on MATLAB[J]. Digital Technology and Application, 2015(4): 82-85.
[19]
黄培. 运动模糊图像复原算法的研究[D]. 西安: 西安科技大学, 2020.
[20]
HuangPei. Research on motion blurred image restoration algorithm[D]. Xi’an: Xi’an University of Science and Technology, 2020.
TangJianya. Design of a panoramic image restoration and target recognition system based on linear array CCD rotary scanning[D]. Nanjing: Nanjing University of Science and Technology, 2016.
YangHuayu, ZhanHuarui. Edge detection algorithm of video image based on median filter technology[J]. Science Technology and Engineering, 2019, 19(9): 143-147.
[25]
陈亦晨. 基于高分遥感的农田生态系统信息提取方法研究[D]. 兰州: 甘肃农业大学, 2020.
[26]
ChenYichen. Method study on extraction of farmland ecosystem’s information based on high-resolution remote sensing[D]. Lanzhou: Gansu Agricultural University, 2020.
[27]
潘长安. 图像边缘检测技术分析[J]. 黑龙江科技信息, 2015(32): 64-65.
[28]
PanChang’an. Analysis of image edge detection technology[J]. Heilongjiang Science and Technology Information, 2015(32): 64-65.
HongXianggong, ChenWei, XiongDi. The research of optimized Roberts algorithm based on heterogeneous CPU/MIC/GPU architecture[J]. Science Technology and Engineering, 2016, 16(36): 217-222.
JiangWangyu, WangLe, YaoYepeng, et al. Multi-scale feature aggregation diffusion and edge information enhancement small object detection algorithm[J]. Computer Engineering and Applications, 2025, 61(7): 105-116.
BaoQilong, JingHuicheng, ZhangJingxuan, et al. Image edge detection method based on improved Canny operator[J]. Modern Electronics Technique, 2024, 47(23): 36-42.