Springe zum Hauptinhalt
Fakultät für Informatik


338. Informatik-Kolloquium

Öffentliche Verteidigung im Rahmen des Promotionsverfahrens

Herr Shadi Saleh, M.Sc.

TU Chemnitz
Fakultät für Informatik
Professur Technische Informatik

"Monocular Depth Estimation with Edge-Based Constraints using Active Learning Optimization"

Donnerstag, 29.02.2024, 11:30 Uhr, Straße der Nationen 62, Böttcher-Bau, 1/336 (neu: A12.336)

Alle interessierten Personen sind herzlich eingeladen!

Poster | .pdf


Depth sensing is pivotal in robotics; however, monocular depth estimation encounters formidable challenges. Existing algorithms, relying on extensive labeled data and large Deep Convolutional Neural Networks (DCNNs), impede real-world applications. We propose two lightweight architectures, attaining commendable accuracy of 91.2% and 90.1%, concurrently reducing the depth error Root Mean Square Error (RMSE) to 4.815 and 5.036. Our lightweight depth model runs at 29-44 FPS on the Jetson Nano GPU, demonstrating efficient performance with minimal power consumption.

Furthermore, we introduce a mask network designed to visualize and analyze the inference of the compact depth network. This aids in the discernment of informative samples for the active learning approach, thereby contributing to heightened model accuracy and enhanced generalization capabilities.

Additionally, our methodology encompasses the introduction of an active learning framework, strategically designed to enhance model performance and accuracy through efficiently utilization of limited labeled training data. This novel framework surpasses antecedent studies by achieving commendable results with a mere 18.3% utilization of the KITTI Odometry dataset. This achievement reflects an adept equilibrium between computational efficiency and accuracy, particularly tailored for cost-effective devices, thereby concurrently diminishing data training requirements.