Abstract
Small object detection is an interesting topic in computer vision. With the rapid development in deep learning, it has drawn attention of several researchers with innovations in approaches to join a race. These innovations proposed comprise region proposals, divided grid cell, multiscale feature maps, and new loss function. As a result, performance of object detection has recently had significant improvements. However, most of the state-of-the-art detectors, both in one-stage and two-stage approaches, have struggled with detecting small objects. In this study, we evaluate current state-of-the-art models based on deep learning in both approaches such as Fast RCNN, Faster RCNN, RetinaNet, and YOLOv3. We provide a profound assessment of the advantages and limitations of models. Specifically, we run models with different backbones on different datasets with multiscale objects to find out what types of objects are suitable for each model along with backbones. Extensive empirical evaluation was conducted on 2 standard datasets, namely, a small object dataset and a filtered dataset from PASCAL VOC 2007. Finally, comparative results and analyses are then presented.
Highlights
Object detection is known as a task that locates all positions of objects of interest in an input by bounding boxes and labeling them into categories that they belong to
Faster RCNN with ResNeXT-101-64 × 4d-feature pyramid networks (FPNs) backbone achieved the top mean average precision (mAP) in two-stage approaches and the top of the table as well, 41.2%
Following [32], methods based on region proposal such as Faster RCNN are better than methods based on regression or classification such as You Only Look Once (YOLO) and Single Shot MultiBox Detector (SSD)
Summary
Object detection is known as a task that locates all positions of objects of interest in an input by bounding boxes and labeling them into categories that they belong to To do this task, several ideas have been proposed from traditional approaches to deep learning-based approaches. E other one includes that in manufacturing industries, the need of detecting assembly parts that are defective or the uncertainty of an angle of view, size of detected object, and deformable shape that significantly changes during assembly process [8]. It illustrates that real-time object detection, applied to the most popular vision-based applications in real world, is really indispensable.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
