BIOENGINEER

Open-source suite exposes how algorithms change porous-stone measurements

An open-source application unifies 14 pore-segmentation methods with colour and ageing analysis, revealing that identical ...
GitHub

cctv-cameras

Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to ...
GitHub

Temporal Focus Memory — code, raw results, and evaluation protocol

Reference implementation, raw result files and the analysis protocol for the manuscript "Temporal Focus Memory for Stable Real-Time Object Detection of Ship Wall-Climbing Robots" (under review at ...
blog.csdn

遥感复试上机实战：从影像读写到分类精度评价的Python全流程

4.1 非监督分类：K-means 上机实现 K-means 是上机考得最多的非监督分类算法。 题目通常给一幅多波段影像，要求分成 K 类，输出分类图。 核心步骤：把影像重塑成 (像素数, 波段数) 的二维数组，用 sklearn.cluster.KMeans 或自己实现，然后重塑回原尺寸。
blog.csdn

YOLOv5单目测距实战：纯Python实现三维距离计算

本文介绍基于YOLOv5与单目摄像头的纯Python三维距离计算方案，核心依赖相机标定参数、目标真实尺寸与针孔模型相似三角形公式，规避solvePnP高开销与姿态敏感问题。重点涵盖高质量标定方法（棋盘格采集规范、重投影误差<0.5像素）、宽度优先的距离估算逻辑、安全系数与焦距均值化等工程优化，并 ...