Computer vision & deep learning blog
Hands-on tutorials and notes on computer vision, deep learning, object detection, and YOLO, with code you can run, by Muhammad Rizwan Munawar.
14 posts
Depth EstimationJuly 27, 2026·9 min readVideo Depth Anything in Python: consistent depth for videoDepth Anything V2 run frame by frame flickers on video. Video Depth Anything fixes that with temporally consistent depth for long clips. Here is how to run it in Python, with the command line and a reusable script.
YOLO26July 19, 2026·19 min readYOLO26 vs YOLO11 vs YOLOv8 vs YOLOv10, YOLOv9 & YOLOv5Six generations of YOLO side by side: published accuracy and parameter counts for YOLOv5, YOLOv8, YOLOv9, YOLOv10, YOLO11 and YOLO26, what actually changed between them, and a straight answer on which one to use for detection, edge deployment, or transfer learning.
OCRJuly 18, 2026·7 min readHow to extract text from images in Python (OCR): 5 libraries comparedA practical guide to reading text from images in Python: Tesseract, EasyOCR, PaddleOCR, docTR and VLM-based OCR, with runnable code and a which-one-to-pick guide.
Object TrackingJuly 18, 2026·8 min readHow to use ByteTrack with YOLO for object tracking in PythonGive YOLO a memory. This tutorial uses ByteTrack to assign persistent IDs to objects across video frames, with a runnable Ultralytics script and a bytetrack.yaml tuning guide.
Semantic SearchJuly 6, 2026·7 min readBuild a semantic image search engine with CLIP and PythonLearn how to build a semantic image search engine that finds pictures by meaning. A few lines of Python turn a folder of images into a searchable index you can query in plain English.
YOLO26July 3, 2026·9 min readYOLO26 vs YOLO11: Real-time ONNX FPS benchmark in PythonBuild one small, reusable class that runs Ultralytics YOLO26 and Ultralytics YOLO11 as ONNX models, draws clean detections, and overlays live FPS and latency so you can compare their real-time speed on the exact same footage.
Depth EstimationJuly 1, 2026·13 min readDepth Anything V2 in Python: image, video and webcam depthLearn how to estimate depth from a single image, a video, or your webcam using Depth Anything V2 and a clean, reusable Python class, plus the run.py command, metric depth, and a note on TensorRT.
Object TrackingJune 27, 2026·13 min readUltralytics object trackers comparison: ByteTrack, BoT-SORT & MoreHow do the six Ultralytics trackers actually behave on the same footage? A look at BoT-SORT, ByteTrack, OC-SORT, Deep OC-SORT, FastTrack, and TrackTrack, their internals, trade-offs, and side-by-side results on ID switches, ID stability, and FPS.
OCRJune 26, 2026·6 min readHow to extract text from images with LightOnOCR and PythonLearn how to read text from images using LightOnOCR, a small and fast vision language model, with a clean and reusable Python class.
YOLO26June 25, 2026·10 min readObject tracking and trajectory forecasting with YOLO26 and ByteTrackDetect, track, and predict the future path of people and vehicles using Ultralytics YOLO26, ByteTrack, and a lightweight velocity-based forecasting model.
YOLO11June 24, 2026·5 min readReal time bird detection and tracking using YOLO11Learn how to detect and track birds using Ultralytics YOLO11 for real-time monitoring and ecological research through computer vision.
YOLO26June 23, 2026·12 min readHow to count people in zones with YOLO26 and OpenCVA practical walkthrough of a compact Python script that detects, tracks, and counts people inside polygon zones using Ultralytics YOLO26 and OpenCV.
YOLO11June 22, 2026·3 min readSupermarket items segmentation and counting with YOLO11Discover how to achieve advanced items segmentation in supermarkets with Ultralytics YOLO11 for efficient object detection and analysis.
SAM2June 21, 2026·3 min readHow to generate accurate segmentation masks using object detection and Meta SAM2Learn how to generate segmentation masks with object detection and SAM2 models for advanced image processing tasks.