Project on Mahdi Sarfarazi

Camera-only 3D tracking and velocity estimation

Sun, 01 Feb 2026 00:00:00 +0000

In this machine-vision course project, I estimated where people and vehicles are in 3D, and how fast they’re moving, using only a phone camera without LiDAR or a stereo rig.

What I built

YOLO11n detects objects and ByteTrack keeps their identities across frames. The metric outdoor variant of Depth Anything V2 then turns each detection into a 3D position.

A recursive Kalman filter tracks motion with a six-value state (position and velocity in x, y, z). It uses wall-clock time between frames, so velocity stays consistent when the frame rate varies, and it keeps predicting through missed detections.

I calibrated the camera (a Samsung A34) with a checkerboard, and used a second phone’s IMU (a Samsung A54, via Phyphox) to sanity-check the estimated velocities.

How I chose the components

I benchmarked the detectors myself on the target laptop (RTX 3060, 6 GB):

Detector	Measured speed
YOLOv8n	≈ 16 FPS
YOLO11n	≈ 20 FPS
YOLO26n	≈ 23 FPS

I picked YOLO11n. It wasn’t the fastest, but it gave the best balance of detection quality, installation reliability and speed. The depth model was the real bottleneck at about 0.22 s per frame (≈ 4.5 FPS).

Results and limits

The Kalman filter typically converged within three to five frames of a new detection. I tested qualitatively on crowded pavements, street traffic and mixed traffic.

The report states the main limitation. Without LiDAR or stereo ground truth, I could not measure end-to-end depth error, and metric scale needed manual calibration. The depth model’s published benchmark (0.454 m MAE on its own validation sets) does not measure this system.

LLM-powered robotic task planning

Mon, 01 Jun 2026 00:00:00 +0000

This is a personal experiment in connecting a language model to a robot safely. The model proposes a plan, and ROS2 executes it on a simulated arm.

What it does

It takes an instruction in plain language and uses the Gemini API to turn it into a sequence of ROS2 actions, which then run on a simulated robotic arm in Gazebo.

Status and limits

This is an early-stage experiment. It has no formal evaluation yet, and the code is not public. I’ll update this page with a repository, the supported task set and results when there is something worth measuring.

The same question drives ViGenX: how to let a language model plan while keeping execution verifiable.

Human-following mobile robot

Sat, 01 Feb 2025 00:00:00 +0000

A course project in which I owned the requirements and the end-to-end build of a small robot that follows a person indoors.

What I built

A Python (Kivy/Buildozer) Android app runs a TensorFlow Lite MobileNet v1 model on the phone to detect and select the person to follow, at roughly 60 frames per second.

The phone sends forward, backward, left, right and stop commands over USB serial to an Arduino Uno, which drives four DC motors through an L298N driver.

An HC-SR04 ultrasonic sensor overrides the vision system. It stops or redirects the robot whenever an obstacle is closer than 1.5 m.

Decisions worth noting

I compared a Raspberry Pi with a smartphone as the compute platform, and SAMURAI, YOLOv8 and MobileNet as detectors, choosing on inference efficiency. Running vision on the phone kept the robot’s electronics simple and cheap.

Limits

This was a course prototype. It was not evaluated with a formal protocol, and no code or video is public.