Improving Accuracy and Efficiency of Object Detection Algorithms Using Multiscale Feature Aggregation Plugins

Rajput, Poonam; Mittal, Sparsh; Narayan, Sarthak

doi:10.1007/978-3-030-58309-5_5

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ideally, feature descriptors provide detailed information of an object and its variations about the background regardless the size of object. Moreover, the provided information by descriptors should be rich in order to enable robust detection or localized of that object [4], [5]. Mainly, there are two main types of feature descriptors: i) global descriptor, ii) local descriptor, where the first one is concerned with visual features as a whole image, while the second one is concerned with a description of patch or part of an image which are specific for localized considerations [6], [7].…”

Section: ì Issn: 2502-4752mentioning

confidence: 99%

Hybrid features for object detection in RGB-D scenes

Awwad

Igried

Wedyan

et al. 2021

IJEECS

View full text Add to dashboard Cite

<div>Object detection is considered a hot research topic in applications of artificial intel-ligence and computer vision. Historically, object detection was widely used in var-ious fields like surveillance, fine-grained activities and robotics. All studies focus on improving accuracy for object detection using images, whether indoor or outdoor scenes. Therefore, this paper took a shot by improving the doable features extraction and proposing crossed sliding window approach using exiting classifiers for object de-tection. In this paper, the contribution includes two parts: First, improving local depth pattern feature along side SIFT and the second part explains a new technique presented by proposing crossed sliding window approach using two different types of images (colored and depth). Two types of features local depth patterns for detection (LDPD) and scale-invariant feature transform (SIFT) were merged as one feature vector. The RGB-D object dataset has been used and it consists of 300 different objects and in-cludes thousands of scenes. The proposed approach achieved high results comparing to other features or separated features that are used in this paper. All experiments and comparatives were applied on the same dataset for the same objective. Experimental results report a high accuracy in terms of detection rate, recall, precision and F1 scorein RGB-D scenes.</div>

show abstract

Section: ì Issn: 2502-4752mentioning

confidence: 99%