Computer Vision
Owlous
Autonomous Vehicle Steering Prediction
Created self-driving car model with LSTM-CNN hybrid architecture for steering angle prediction from 70+ hours of dash-cam data. Synchronized multi-camera inputs via NVIDIA DRIVE PX and implemented YOLO for lane detection and object tracking. Optimized inference latency by 40% through TensorRT quantization, enabling 60 FPS decision-making on embedded systems.
6 months
Project Duration
<1.5° mean absolute error
Key Achievement
5+
Technologies Used
The Challenge
Insight Fusion Analytics required a sophisticated social network analysis system to predict user connections and relationships at scale for their platform with 500k+ users.
The Solution
Implemented advanced graph algorithms including PageRank, Katz Centrality, and Adar Index, combined with Random Forest classification and Matrix Factorization for scalable link prediction.
Results & Impact
- Achieved 92% F1-score in link prediction
- Successfully scaled to 500k+ users
- Maintained 88% precision and 85% recall
- Improved user engagement by 30%
Project Metrics
<1.5° mean absolute error
40% inference latency optimization
60 FPS decision-making
Technologies Used
LSTM-CNNNVIDIA DRIVE PXYOLOTensorRTMulti-camera
Project Details
Company
Owlous
Duration
6 months
Team Size
3 engineers + 1 data scientist
Category
Computer Vision