Dec 13, 2025 · 5 min read · The emergence of multimodal systems capable of processing both visual and linguistic input has created new opportunities for natural human-computer interaction. However, real-time computer vision models operate at frame rates measured in milliseconds...
Join discussion
Oct 29, 2025 · 4 min read · Introduction Traffic monitoring in urban environments is evolving from mere recognition to anomaly detection identifying behaviours that deviate from the norm. In this project, we present a system that monitors live CCTV streams of pedestrian zones, ...
Join discussion
May 30, 2025 · 4 min read · project link- Khushhiii08/Smart-Retail-Product-Detection-and-Analysis-Using-YOLOv8 This is one of the most personal and intense projects I’ve worked on — a rollercoaster of anxiety, fried laptops, and that one glorious day everything finally worked. ...
Join discussionApr 15, 2025 · 4 min read · When I joined ResoluteAI as a Deep Learning Engineer Intern, I didn’t just want to train models and get good accuracy. I wanted to build things that actually solved field-level problems — systems that could help real businesses save time, automate te...
Join discussionFeb 25, 2025 · 2 min read · Client: Digital Content Creator & Marketing AgencyDuration: 2 WeeksRole: Machine Learning Engineer & Computer Vision Specialist 🚀 Project Overview The client, a marketing agency specializing in digital content and advertising, needed an AI-powered i...
Join discussion
Feb 2, 2025 · 1 min read · I know the hype is all around LLMs right now, but deep learning for computer vision continues to drive advancements in AI too – from your smartphone to applications at airports. Perhaps you would like to learn how to build yours. This past summer, I ...
Join discussion
Sep 27, 2024 · 1 min read · 系统组成 视频AI识别系统,该系统主要由四个部分组成,分别为:admin管理端，media流媒体端，分析端analyzer(c++)和YOLOV8模型端.系统当中四个模块之间的关系如下图: 管理端Admin模块 admin模块主要功能就是负责前后端的交互功能,其中使用的是Web作为前端的展示,后端的数据和接口的处理逻辑为Django的框架,负责执行一些自动化操作,和实现与临时数据库Redis之间的交互功能,包括:账号登陆,视频流id,报警视频和报警图片等信息的存储. MediaServer媒...
Join discussionSep 16, 2024 · 4 min read · Overview This project demonstrates how to perform object tracking and annotation using YOLO (You Only Look Once) on a video, leveraging Google Colab for efficient processing and Google Drive for saving outputs. The entire process involves downloading...
Join discussion
Aug 29, 2024 · 1 min read · Few months ago I wrote an article and showed, that it's possible to run YOLOv8 object detection using not only Python, but any other language, that supports ONNX. I also provided an example of object detection web applications on Julia, JavaScript, N...
Join discussion
Aug 16, 2024 · 4 min read · In today's fast-paced medical environment, efficiency is key. With advancements in AI, we're now able to streamline complex tasks, making them faster and more accurate. One such task is the analysis and reporting of MRI images. In this post, I'll wal...
Join discussion