63 skills found · Page 1 of 3
ShareX / ShareXShareX is a free and open-source application that enables users to capture or record any area of their screen with a single keystroke. It also supports uploading images, text, and various file types to a wide range of destinations.
MathewSachin / CapturaCapture Screen, Audio, Cursor, Mouse Clicks and Keystrokes
aardio / Gif123Record an area of your desktop to a GIF, easily copy and paste it wherever you want.
realskyrin / Capcap⌘⌘ - A lightweight, native macOS screenshot tool that lives in your menu bar. Double-tap ⌘ Command to capture any region of your screen — instantly copied to clipboard, or annotate first with pen and mosaic tools.
maximrouf / RegionCapturePlugin for Unity 6000 (for mobile and desktop app's)
yeahitsjan / PawxelLightweight screenshot tool for designers & developers
gavinkendall / AutoscreenAn automated screen capture utility for Windows that takes screenshots at a set interval to monitor activity
airar-dev / Unity AR ColorMappingUnity AR Colormapping for easyar,vuforia,maxstar, arkit, arcore
stevenhoving / CamstudioCamStudio fork
PangMo5 / SwiftyCrowFully on-device on-screen translator for macOS: region capture and live overlay, powered by Vision OCR and Apple Translation
jamesmontemagno / Tiny ClipsA lightweight macOS & Windows menu bar app for capturing screenshots (PNG), video (MP4), and animated GIFs of a selected screen region.
DebadityaQU / RDDMIn this work, we introduce Region-Disentangled Diffusion Model (RDDM), a novel diffusion model designed to capture the complex temporal dynamics of ECG.
iSoldLeo / MioA native macOS screenshot tool that freezes every display in under 80 ms when you press the hotkey — pick a window, a region, or a whole screen from still frames. Window captures keep their transparent rounded corners. Built-in editor for annotations. Menu bar only, fully offline.
Speiser / Dot ScreencapA screencapturing library
thesleepingsage / Hypr LensA standalone, portable toolkit that provides a polished region selector UI with window detection, screenshot capture, OCR text extraction, Google Lens integration, and screen recording.
radhe-raman-tiwari / Rice Crop Insects And Weed Detection Using Faster R CNNAs the increase in the world population the demand of the rice is also increases. In order to increase the growth of rice in the rice crop it is necessary to detect the weed and insects in the rice crop to minimize the growth of weed and insects so that the growth of the rice can be increased.Insect and Weed detection is the important factor to be analyzed. Unmanned Air Vehicle (UAV) is used for data acquisition of rice crop in different phases and states so that high quality of RGB images can be captured. In which we have taken 15 different types of rice crop insects species images and different phases of weed images to train the model. The proposed method facilitates the extraction of weed and insects into the rice crop field using deep learning concept faster region-based convolutional neural networks(Faster R-CNNs) it is implemented using Python3 with the help of Tensorflow API. The result shows that Faster R-CNN method is the state of arts method for detection and classification of weed and insects with good accuracy rate.
gilyes / Screenshot.NETSimple screenshot library for .NET (Windows only). Allows selection and capture of screen region, similar to Snipping Tool.
sadopc / ScreenCaptureNative macOS menu bar app for capturing and annotating screenshots. Features include full-screen/region capture, annotation tools (rectangles, arrows, freehand, text), multi-monitor support, and quick export. Built with Swift 6, SwiftUI, and ScreenCaptureKit.
TAKU-ZE / Screenshot TranslatorDesktop screenshot OCR + on-the-fly translation suite. Capture any region with a hotkey, run cloud Vision-Language Model OCR, translate, and overlay Markdown-styled HTML back onto your selection. PyQt5 + SiliconFlow.
cci9 / IOUCalculationIOU Calculation for 2D Quadrilaterals The major functional components of autonomous vehicles are perception, control, planning, system management, and localization. Perception is a process that senses the surrounding environment using various sensors like Radars, LiDARs, Ultrasonic and Cameras sensors. Sensors are designed to extract information from the environment and hence, to perceive the surroundings. • Lidars are used to extract the information on the position and shape of surrounding obstacles within its range and field of view (FOV). • Camera sensor data provides information about the object class. • Radars are used to derive the position and velocity of the obstacles and so on. Multi-sensor fusion integrates the sequence of observations from a number of heterogeneous sensors into a single best estimate of the state of the environment. One of the Sensor Fusion outputs is the IOU (Intersection over Union) or Jaccard index during the object detection. When the object detection is performed through more than one source of sensors (such as Ultrasonic and Camera sensors), the IOU or Jaccard index is calculated to quantify the percent overlap from two different sources of sensors. The basic problem in multi-sensor fusion systems is to integrate a sequence of observations from a number of different sensors into a single best estimate of the state of the environment. In such a case, the IOU helps to identify the overlap area, which is captured from the multi-sensors. For example for the Autonomous Parking Functionality of ADAS (Autonomous Driving Assistance System), the Ultrasonic and Camera sensors are capturing the free space for Ego Vehicle Parking (as shown in the below figure). As per the capability and mounting position of different sensors, the available parking space is captured. The captured area from different sensors may or may not be the same. In that case, the IOU or Jaccard Index helps to quantify the overlap area detected by two different sensors. Figure 1: Practical use case of IOU The IOU or Jaccard Index is calculated as follows: Figure 2: IOU Calculation The IOU (Intersection over Union) value varies between 0 to 1. More the overlap region better the IOU value. Henceforth the confidence in the input data from the sensors increases. Lower the IOU, troubles in deciding the available space for the parking as different sensors are showing different spaces for parking. Figure 3: Confidence decision based on IOU Note: Decision of the High Confidence from calculated IOU value varies from application to application. For example, in some applications, High Confidence can be decided over 0.8 IOU value whereas, in some other applications, High Confidence can be decided over 0.9 IOU value. The IOU calculation can be done over the images or coordinates captured from the different sensors. In addition, the IOU calculation can also be performed considering the captured object as a 2D or 3D object. In this article, I have focused on the IOU calculation based on coordinates received from two different sensors. The captured coordinates would be of 2D Quadrilateral. Refer to the MATLAB Code for the Calculation of IOU using the X and Y coordinates captured from the two different sensors. The point of interest here is in finding the intersection points and identifying the quadrilateral vertices that lie inside another quadrilateral. A glimpse of the MATLAB code results: Figure 4: IOU calculation from MATLAB Code I have considered all the possible conditions for regular/irregular quadrilateral such as complete overlapping, no overlapping, vertices having negative and positive coordinates, and so on. Thank you for reading. I am open to discussion on this topic. Do reach out to me at chetan9chudhari@gmail.com. HAPPY LEARNING!!!
