2022/06/07 by Luca Ciampi, Ciampi, Luca
Computer Science · #Adaptation (eye) #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Convolutional neural network #Deep learning #Deep neural networks #Domain (mathematical analysis) #Domain adaptation #FOS: Computer and information sciences #Human Pose and Action Recognition #Inference #Labeled data #Machine learning #Scalability #USable #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.2206.03033
published in arXiv (Cornell University) (Cornell University) · Version with high-quality images can be found at https://etd.adm.unipi.it/theses/available/etd-04262022-163702/. arXiv admin note: text overlap with arXiv:1802.03601, arXiv:1707.01202, arXiv:1809.02165, arXiv:1901.06026, arXiv:1808.01244 by other authors
openalex publication_date 2022/06/07 · arxiv created 2022/06/08 · arxiv updated 2022/06/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this dissertation, we investigated and enhanced Deep Learning (DL) techniques for counting objects, like pedestrians, cells or vehicles, in still images or video frames. In particular, we tackled the challenge related to the lack of data needed for training current DL-based solutions. Given that the budget for labeling is limited, data scarcity still represents an open problem that prevents the scalability of existing solutions based on the supervised learning of neural networks and that is responsible for a significant drop in performance at inference time when new scenarios are presented to these algorithms. We introduced solutions addressing this issue from several complementary sides, collecting datasets gathered from virtual environments automatically labeled, proposing Domain Adaptation strategies aiming at mitigating the domain gap existing between the training and test data distributions, and presenting a counting strategy in a weakly labeled data scenario, i.e., in the presence of non-negligible disagreement between multiple annotators. Moreover, we tackled the non-trivial engineering challenges coming out of the adoption of Convolutional Neural Network-based techniques in environments with limited power resources, introducing solutions for counting vehicles and pedestrians directly onboard embedded vision systems, i.e., devices equipped with constrained computational capabilities that can capture images and elaborate them.