Deep Learning Specialization · Convolutional Neural Networks

YOLO Car Detection for Autonomous Driving

An object-detection milestone using YOLO-style outputs, score filtering, IoU, and non-max suppression to detect cars and road objects.

YOLOBounding boxesIoUNon-max suppressionObject detection

GitHub

What this project is about

YOLO combines localization and classification in one dense prediction grid. The project implements score filtering, IoU calculation, non-max suppression, box conversion, and drawing final detections.

Implementation focus

The key learning was that object detection is a post-processing pipeline as much as a neural network: raw predictions must be filtered, ranked, scaled, and interpreted correctly.

Key results and artifacts

Input size: 608×608×3
Model output: 19×19×5×85
Prediction used score threshold 0.3 and IoU threshold 0.5
Example: found 10 boxes in a test image

What I learned

This project connected CNNs to real perception systems: localization, confidence scores, class prediction, and filtering all need to work together.

Milestone deep dive

What this project proves in my learning path.

An object-detection milestone using YOLO-style outputs, score filtering, IoU, and non-max suppression to detect cars and road objects. The milestone is included because it shows a complete learning unit: a problem, a data representation, an implementation path, measurable outputs, and a lesson that later connects to larger AI systems.

Input layerimages, anchors, boxes, and class scores

Model layerYOLO-style detection pipeline with filtering and NMS

Evaluation layertests, metrics, plots, or qualitative output

Artifact layerlocalized objects with confidence scores

Problem framing

What I was trying to solve

This page is not just a lab description. It explains how I transformed the assignment idea into an engineering story: what the model receives, what it optimizes, what output it should produce, and how the result can be inspected.

Implementation

What I coded or assembled

The implementation focus was the mechanism behind the result: functions, model blocks, training logic, preprocessing, evaluation, and the small technical details that make the notebook work rather than only look correct.

Concepts

Core concepts

YOLOBounding boxesIoUNon-max suppressionObject detection

These tags show the technical ideas this milestone added to my toolkit.

Learning result

What changed after it

This project connected CNNs to real perception systems: localization, confidence scores, class prediction, and filtering all need to work together.

Important outputs and evidence

Input size: 608×608×3
Model output: 19×19×5×85
Prediction used score threshold 0.3 and IoU threshold 0.5
Example: found 10 boxes in a test image

How I would explain it in an interview

I would describe this milestone by starting from the data representation, then explain the model or algorithm, then show what was measured. The important part is not only the final number; it is the ability to reason about why the method works, what assumptions it makes, and what limitations should be improved next.