Occlusion Handling in Generic Object Detection: A Review

Saleh, Kaziwa; Szénási, Sándor; Vamossy, Zoltan

doi:10.1109/sami50585.2021.9378657

Cited by 40 publications

(19 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies (Li et al 2021;Yan et al 2020;Najibi et Occlusion handling in computer vision. The negative impact of occlusion on various computer vision tasks, including tracking (Liu et al 2018), image-based pedestrian detection (Zhang et al 2018), image-based car detection (Reddy et al 2019) and semantic part detection (Saleh et al 2021), is acknowledged. Efforts addressing occlusion include the amodal instance segmentation (Follmann et al 2019), the Multi-Level Coding that predicts the presence of occlusion (Qi et al 2019b).…”

Section: Related Workmentioning

confidence: 99%

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Zhong

Neumann

2022

AAAI

111

View full text Add to dashboard Cite

Advances in LiDAR sensors provide rich 3D data that supports 3D scene understanding. However, due to occlusion and signal miss, LiDAR point clouds are in practice 2.5D as they cover only partial underlying shapes, which poses a fundamental challenge to 3D perception. To tackle the challenge, we present a novel LiDAR-based 3D object detection model, dubbed Behind the Curtain Detector (BtcDet), which learns the object shape priors and estimates the complete object shapes that are partially occluded (curtained) in point clouds. BtcDet first identifies the regions that are affected by occlusion and signal miss. In these regions, our model predicts the probability of occupancy that indicates if a region contains object shapes and integrates this probability map with detection features and generates high-quality 3D proposals. Finally, the occupancy estimation is integrated into the proposal refinement module to generate accurate bounding boxes. Extensive experiments on the KITTI Dataset and the Waymo Open Dataset demonstrate the effectiveness of BtcDet. Particularly for the 3D detection of both cars and cyclists on the KITTI benchmark, BtcDet surpasses all of the published state-of-the-art methods by remarkable margins. Code is released.

show abstract

Section: Related Workmentioning

confidence: 99%

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Zhong

Neumann

2022

AAAI

111

View full text Add to dashboard Cite

show abstract

“…Despite their ability to achieve high segmentation accuracy in simple environments, the majority of the existing approaches to object segmentation suffer to correctly segment objects of interest in cluttered environments, under various illumination conditions, an in presence of occlusions [17]. Depending on the environment, the size of the object in the observed scene, and the camera's field of view, different parts of the object of interest may be occluded [18]. Hence, for successful object segmentation, it is necessary to recover or at least predict the occluded part of the object prior to object detection, which is challenging to achieve.…”

Section: Introductionmentioning

confidence: 99%

CM-UNet: ConvMixer UNet for Segmentation of Unknown Objects in Cluttered Scenes

et al. 2022

View full text Add to dashboard Cite

Object segmentation in cluttered environments is a fundamental pre-processing step for many perception-related tasks such as vision-based robotic grasping. Most of the existing object segmentation methods are incapable of precisely segmenting unknown objects, particularly in scenarios exhibiting significant occlusion. In this paper, we propose a novel approach for refining the segmentation of unknown objects in cluttered scenes. More specifically, a ConvMixer-based UNet model is designed to enhance the segmentation mask and boundary of unknown objects appearing in cluttered scenes. In our model, we leverage the object's semantic and localization information, which are essential for successful segmentation, using a ConvMixer-based Cross Fusion (CMCF) module. Furthermore, we propose to use patch embedding as a pre-processing step, where input data is rearranged to expedite processing and improve the efficiency of the system. CM-UNet was trained and extensively tested on various challenging publicly available datasets, including unknown objects in un-structured scenes. Thorough evaluations, in terms of segmentation accuracy and processing efficiency, were conducted against state-of-the-art solutions, where the superiority of our model was proven. CM-UNet has shown its ability to efficiently improve the segmentation accuracy of unknown objects in cluttered scenes, even in presence of occlusion.

show abstract

“…In the case of occlusion [19], it might be either intra-class occlusion or inter-class occlusion. The intra-class occlusion happens when the interesting object is hidden by the same category of object such as crowded people.…”

Section: Introductionmentioning

confidence: 99%

“…else19 Reject this window as a human; 20 where P is the pixel sizes of an image size, N scale is the number of scales in image pyramid, N block is the number of the block in each window image, N cell is the number of cell in each block, and N bin is the direction in each cell.…”

mentioning

confidence: 99%

Anthropometric Ratios for Lower-Body Detection Based on Deep Learning and Traditional Methods

2022

View full text Add to dashboard Cite

Lower-body detection can be useful in many applications, such as the detection of falling and injuries during exercises. However, it can be challenging to detect the lower-body, especially under various lighting and occlusion conditions. This paper presents a novel lower-body detection framework using proposed anthropometric ratios and compares the performance of deep learning (convolutional neural networks and OpenPose) and traditional detection methods. According to the results, the proposed framework helps to successfully detect the accurate boundaries of the lower-body under various illumination and occlusion conditions for lower-limb monitoring. The proposed framework of anthropometric ratios combined with convolutional neural networks (A-CNNs) also achieves high accuracy (90.14%), while the combination of anthropometric ratios and traditional techniques (A-Traditional) for lower-body detection shows satisfactory performance with an averaged accuracy (74.81%). Although the accuracy of OpenPose (95.82%) is higher than the A-CNNs for lower-body detection, the A-CNNs provides lower complexity than the OpenPose, which is advantageous for lower-body detection and implementation on monitoring systems.

show abstract

Occlusion Handling in Generic Object Detection: A Review

Cited by 40 publications

References 75 publications

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

CM-UNet: ConvMixer UNet for Segmentation of Unknown Objects in Cluttered Scenes

Anthropometric Ratios for Lower-Body Detection Based on Deep Learning and Traditional Methods

Contact Info

Product

Resources

About