Occlusion Handling in Generic Object Detection: A Review

  title={Occlusion Handling in Generic Object Detection: A Review},
  author={K. Saleh and S{\'a}ndor Sz{\'e}n{\'a}si and Zolt'an V'amossy},
  journal={2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)},
The significant power of deep learning networks has led to enormous development in object detection. Over the last few years, object detector frameworks have achieved tremendous success in both accuracy and efficiency. However, their ability is far from that of human beings due to several factors, occlusion being one of them. Since occlusion can happen in various locations, scale, and ratio, it is very difficult to handle. In this paper, we address the challenges in occlusion handling in… Expand

Figures from this paper


Deep Learning for Generic Object Detection: A Survey
A comprehensive survey of the recent achievements in this field brought about by deep learning techniques, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. Expand
Survey of pedestrian detection with occlusion
The main ideas and core problems of each method model are analyzed and discussed and an outlook on the problems to be solved in the future development of pedestrian detection technology with occlusion is given. Expand
Object Detection With Deep Learning: A Review
This paper provides a review of deep learning-based object detection frameworks and focuses on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. Expand
Robust Object Detection Under Occlusion With Context-Aware CompositionalNets
The proposed model can detect objects robustly, increasing the detection performance of strongly occluded vehicles from PASCAL3D+ and MS-COCO by 41% and 35% respectively in absolute performance relative to Faster R-CNN. Expand
Inferring occluded features for fast object detection
The experimental results demonstrate the effectiveness of the proposed method both in improving the classification performance and achieving a fairly high processing speed. Expand
DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion
DeepVoting is presented, which incorporates the robustness shown by [25] into a deep network, so that the whole pipeline can be jointly optimized and enjoys explainability as the detection results can be diagnosed via looking up the voting cues. Expand
Faster Bounding Box Annotation for Object Detection in Indoor Scenes
An approach for rapid bounding box annotation for object detection datasets, which trains deep learning based object detectors with a number of state-of-the-art models and compares them in terms of speed and accuracy. Expand
Synthesizing Training Data for Object Detection in Indoor Scenes
This work charts new opportunities for training detectors for new objects by exploiting existing object model repositories in either a purely automatic fashion or with only a very small number of human-annotated examples. Expand
Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd
A new occlusion-aware R-CNN (OR-CNN) is proposed to improve the detection accuracy in the crowd and a new aggregation loss is designed to enforce proposals to be close and locate compactly to the corresponding objects. Expand
Detecting Semantic Parts on Partially Occluded Objects
Experiments show that the algorithm outperforms several competitors in semantic part detection when occlusions are present, and uses a simple voting method, based on log-likelihood ratio tests and spatial constraints, to combine the evidence of local cues. Expand