Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes

Yang, Chenhongyi; Ablavsky, Vitaly; Wang, Kaihong; Feng, Qianjin; Betke, Margrit

doi:10.1007/978-3-030-58523-5_31

Cited by 11 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some essentially identical NMS algorithms are shown in Figure 9, which shows the similarities and differences between different NMS algorithms. What's more, some other NMS strategies are proposed to adapt to their own methods such as joint NMS [60], set NMS [80], Beta NMS [70], SG NMS [73], pos NMS [97] and CAS NMS [82].…”

Section: Loss-based and Post-processing Methodsmentioning

confidence: 99%

Occlusion Handling and Multi-Scale Pedestrian Detection Based on Deep Learning: A Review

Fang

Liu

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Pedestrian detection is an important branch of computer vision, and it has important applications in the fields of autonomous driving, artificial intelligence and video surveillance. With the rapid development of deep learning and the proposal of large-scale datasets, pedestrian detection has reached a new stage and achieves better performance. However, the performance of state-of-the-art methods is far behind the expectation, especially when occlusion and scale variance exist. Therefore, a lot of works focused on occlusion and scale variance have been proposed in the past few years. The purpose of this article is to make a detailed review of recent progress in pedestrian detection. Firstly, brief progress of pedestrian detection in the past two decades is summarized. Secondly, recent deep learning methods focusing on occlusion and scale variance are analyzed. Moreover, the popular datasets and evaluation methods for pedestrian detection are introduced. Finally, the development trend of pedestrian detection is prospected.

show abstract

Section: Loss-based and Post-processing Methodsmentioning

confidence: 99%

Occlusion Handling and Multi-Scale Pedestrian Detection Based on Deep Learning: A Review

Fang

Liu

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Yang et al [24] introduced the Semantics-Geometry Non-Maximum-Suppression (SG-NMS) algorithm as part of the Serial R-FCN network [68], aiming to enhance object detection through a heuristic-based approach. This two-stage detector combines bounding boxes based on detection scores obtained from the Serial R-FCN, suppressing overlapping boxes with lower scores.…”

Section: Two-stage Detector Algorithmsmentioning

confidence: 99%

Enhancing Object Detection in Smart Video Surveillance: A Survey of Occlusion-Handling Approaches

Ouardirhi,

Mahmoudi,

Zbakh

2024

Electronics

View full text Add to dashboard Cite

Smart video surveillance systems (SVSs) have garnered significant attention for their autonomous monitoring capabilities, encompassing automated detection, tracking, analysis, and decision making within complex environments, with minimal human intervention. In this context, object detection is a fundamental task in SVS. However, many current approaches often overlook occlusion by nearby objects, posing challenges to real-world SVS applications. To address this crucial issue, this paper presents a comprehensive comparative analysis of occlusion-handling techniques tailored for object detection. The review outlines the pretext tasks common to both domains and explores various architectural solutions to combat occlusion. Unlike prior studies that primarily focus on a single dataset, our analysis spans multiple benchmark datasets, providing a thorough assessment of various object detection methods. By extending the evaluation to datasets beyond the KITTI benchmark, this study offers a more holistic understanding of each approach’s strengths and limitations. Additionally, we delve into persistent challenges in existing occlusion-handling approaches and emphasize the need for innovative strategies and future research directions to drive substantial progress in this field.

show abstract

“…Except for the most prevalent Gree-dyNMS, multiple improved variants have been proposed recently. Generally, they can be categorized into three groups: 1) Criterion-based (Jiang et al 2018;Tychsen-Smith and Petersson 2018;Tan et al 2019;Yang et al 2019a): they utilize other scores instead of classification confidence as the criterion to remove bboxes by NMS, e.g., IoU scores. 2) Learning-based (Hosang, Benenson, and Schiele 2017;Hu et al 2018): they directly learn an extra network to remove duplicate bboxes.…”

Section: Related Workmentioning

confidence: 99%

Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding

Chen

Xiao

et al. 2021

AAAI

View full text Add to dashboard Cite

The prevailing framework for solving referring expression grounding is based on a two-stage process: 1) detecting proposals with an object detector and 2) grounding the referent to one of the proposals. Existing two-stage solutions mostly focus on the grounding step, which aims to align the expressions with the proposals. In this paper, we argue that these methods overlook an obvious mismatch between the roles of proposals in the two stages: they generate proposals solely based on the detection confidence (i.e., expression-agnostic), hoping that the proposals contain all right instances in the expression (i.e., expression-aware). Due to this mismatch, current two-stage methods suffer from a severe performance drop between detected and ground-truth proposals. To this end, we propose Ref-NMS, which is the first method to yield expression-aware proposals at the first stage. Ref-NMS regards all nouns in the expression as critical objects, and introduces a lightweight module to predict a score for aligning each box with a critical object. These scores can guide the NMS operation to filter out the boxes irrelevant to the expression, increasing the recall of critical objects, resulting in a significantly improved grounding performance. Since Ref- NMS is agnostic to the grounding step, it can be easily integrated into any state-of-the-art two-stage method. Extensive ablation studies on several backbones, benchmarks, and tasks consistently demonstrate the superiority of Ref-NMS. Codes are available at: https://github.com/ChopinSharp/ref-nms.

show abstract

Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes

Cited by 11 publications

References 40 publications

Occlusion Handling and Multi-Scale Pedestrian Detection Based on Deep Learning: A Review

Occlusion Handling and Multi-Scale Pedestrian Detection Based on Deep Learning: A Review

Enhancing Object Detection in Smart Video Surveillance: A Survey of Occlusion-Handling Approaches

Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding

Contact Info

Product

Resources

About