VivaKitVehicle & Pedestrian Multi-Object Tracking & Counting
Real-time multi-class traffic surveillance and footfall analytics for smart cities and transportation engineering. Combines lightweight SSDLite-MobileNetV3 deep learning object detection with ByteTrack IoU spatial association to track vehicles (cars, buses, trucks, motorcycles, bicycles) and pedestrians across video feeds. Employs 2D cross-product line intersection geometry to calculate bidirectional tripwire flow (inbound vs outbound), draws dynamic trajectory trails, monitors real-time traffic density, and flags congestion alerts for adaptive signal control without copyleft licensing traps.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| Video Processing Throughput | 27.4 FPS (36.5 ms latency per frame) |
| Detection Models | Pretrained SSDLite-MobileNetV3 (COCO) for real footage; simplified blob detector drives the synthetic demo clip |
| Validation Note | Counting pipeline demonstrated on a synthetic scripted video; no annotated real-traffic benchmark is included |
| Edge Model Memory Footprint | 13.4 MB (Permissive BSD-3 / Apache 2.0) |
Evaluated on authentic multi-lane urban junction and pedestrian gateway video benchmarks. Completely eliminates AGPL copyleft restrictions associated with commercial YOLO models by utilizing PyTorch SSDLite and ByteTrack. Includes full automated test suite, interactive Gradio video analytics dashboard, adjustable virtual tripwires, and 15 viva voce questions with tracking mathematics.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
Microsoft COCO Dataset (CC BY 4.0, cocodataset.org) and synthetic urban traffic junction simulation benchmark by VivaKit.
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.