Determining noise performance of co-occurrence GMuLBP on object detection task

2013 ◽  
Author(s):  
Nuh Alpaslan ◽  
Mehmet Murat Turhan ◽  
Davut Hanbay
Keyword(s):  
Object Detection ◽  
Detection Task ◽  
Noise Performance

scholarly journals One For All: A Mutual Enhancement Method for Object Detection and Semantic Segmentation

2019 ◽  
Vol 10 (1) ◽  
pp. 13 ◽  
Author(s):  
Shichao Zhang ◽  
Zhe Zhang ◽  
Libo Sun ◽  
Wenhu Qin
Keyword(s):  
Object Detection ◽  
Data Augmentation ◽  
Semantic Segmentation ◽  
Detection Task ◽  
Training Set ◽  
Segmentation Accuracy ◽  
Enhancement Method ◽  
Road Segmentation ◽  
Accuracy Performance

Generally, most approaches using methods such as cropping, rotating, and flipping achieve more data to train models for improving the accuracy of detection and segmentation. However, due to the difficulties of labeling such data especially semantic segmentation data, those traditional data augmentation methodologies cannot help a lot when the training set is really limited. In this paper, a model named OFA-Net (One For All Network) is proposed to combine object detection and semantic segmentation tasks. Meanwhile, using a strategy called “1-N Alternation” to train the OFA-Net model, which can make a fusion of features from detection and segmentation data. The results show that object detection data can be recruited to better the segmentation accuracy performance, and furthermore, segmentation data assist a lot to enhance the confidence of predictions for object detection. Finally, the OFA-Net model is trained without traditional data augmentation methodologies and tested on the KITTI test server. The model works well on the KITTI Road Segmentation challenge and can do a good job on the object detection task.

scholarly journals Evaluation of adaption skills in older adults using behavioural and EEG repeated measurements during a visual oddball object detection task

2020 ◽  
Vol 16 (S5) ◽  
Author(s):  
Laura M. Rueda Delgado ◽  
Hugh Nolan ◽  
Alison R Buick ◽  
Florentine Barbey ◽  
John Dyer ◽  
...  
Keyword(s):  
Older Adults ◽  
Object Detection ◽  
Detection Task ◽  
Repeated Measurements ◽  
Visual Oddball

Developing a Driving Simulator Based Functional Object Detection Task

2012 ◽  
Vol 26 (4) ◽  
pp. 240-256
Author(s):  
Richard R. Goodenough ◽  
Johnell O. Brooks ◽  
Matthew C. Crisler ◽  
Patrick J. Rosopa
Keyword(s):  
Object Detection ◽  
Driving Simulator ◽  
Detection Task ◽  
Functional Object

scholarly journals Optimized loss functions for object detection and application on nighttime vehicle detection

2021 ◽  
pp. 095440702110363
Author(s):  
Shang Jiang ◽  
Haoran Qin ◽  
Bingli Zhang ◽  
Jieyu Zheng
Keyword(s):  
Object Detection ◽  
Loss Function ◽  
Mahalanobis Distance ◽  
Vehicle Detection ◽  
Detection Task ◽  
Loss Functions ◽  
Detection Accuracy ◽  
Localization Accuracy ◽  
Detection Speed

The loss function is a crucial factor that affects the detection precision in the object detection task. In this paper, we optimize both two loss functions for classification and localization simultaneously. Firstly, we reconstruct the classification loss function by combining the prediction results of localization, aiming to establish the correlation between localization and classification subnetworks. Compared to the existing studies, in which the correlation is only established among the positive samples and applied to improve the localization accuracy of predicted boxes, this paper utilizes the correlation to define the hard negative samples and then puts emphasis on the classification of them. Thus the whole misclassified rate for negative samples can be reduced. Besides, a novel localization loss named MIoU is proposed by incorporating a Mahalanobis distance between the predicted box and target box, eliminating the gradients inconsistency problem in the DIoU loss, further improving the localization accuracy. Finally, the proposed methods are applied to train the networks for nighttime vehicle detection. Experimental results show that the detection accuracy can be outstandingly improved with our proposed loss functions without hurting the detection speed.

Age Differences in Visual Abilities in Nighttime Driving Field Conditions

1996 ◽  
Vol 40 (18) ◽  
pp. 923-927 ◽  
Author(s):  
Susan T. Chrysler ◽  
Suzanne M. Danielson ◽  
Virginia M. Kirby
Keyword(s):  
Object Detection ◽  
Age Differences ◽  
Age Groups ◽  
Negative Contrast ◽  
Detection Task ◽  
Small Object ◽  
Case Scenario ◽  
Worst Case ◽  
Front Passenger ◽  
Nighttime Driving

This study was conducted to provide field data on age differences in sign legibility and object detection. Two age groups of healthy drivers with normal vision were tested for nighttime visual ability. The older group had an average age of 65.6 years and the younger group averaged 22.5 years. The field study was conducted on a private road with the subjects seated in the front passenger seat. Subjects performed a Landolt ring legibility task for four types of signs; positive and negative contrast, new and worn material. Subjects also performed object detection tasks using a small object and a pedestrian target appearing in average and low reflectance. In addition, sign legibility and object detection were completed for some trials using a simulated inclement weather visor to create a worst-case scenario. The object detection task was also completed in the presence of glare from oncoming headlamps. Results showed that older driver's legibility distances were 65% those of the younger drivers. Age differences in the object detection task ranged from a 20% to a 45% reduction for older drivers across visibility conditions.

scholarly journals Subtask Attention Based Object Detection in Remote Sensing Images

2021 ◽  
Vol 13 (10) ◽  
pp. 1925
Author(s):  
Shengzhou Xiong ◽  
Yihua Tan ◽  
Yansheng Li ◽  
Cai Wen ◽  
Pei Yan
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Feature Fusion ◽  
Detection Task ◽  
Feature Representation ◽  
Detection Accuracy ◽  
Remote Sensing Images ◽  
Attention Network ◽  
Multi Scale ◽  
Automatic Interpretation

Object detection in remote sensing images (RSIs) is one of the basic tasks in the field of remote sensing image automatic interpretation. In recent years, the deep object detection frameworks of natural scene images (NSIs) have been introduced into object detection on RSIs, and the detection performance has improved significantly because of the powerful feature representation. However, there are still many challenges concerning the particularities of remote sensing objects. One of the main challenges is the missed detection of small objects which have less than five percent of the pixels of the big objects. Generally, the existing algorithms choose to deal with this problem by multi-scale feature fusion based on a feature pyramid. However, the benefits of this strategy are limited, considering that the location of small objects in the feature map will disappear when the detection task is processed at the end of the network. In this study, we propose a subtask attention network (StAN), which handles the detection task directly on the shallow layer of the network. First, StAN contains one shared feature branch and two subtask attention branches of a semantic auxiliary subtask and a detection subtask based on the multi-task attention network (MTAN). Second, the detection branch uses only low-level features considering small objects. Third, the attention map guidance mechanism is put forward to optimize the network for keeping the identification ability. Fourth, the multi-dimensional sampling module (MdS), global multi-view channel weights (GMulW) and target-guided pixel attention (TPA) are designed for further improvement of the detection accuracy in complex scenes. The experimental results on the NWPU VHR-10 dataset and DOTA dataset demonstrated that the proposed algorithm achieved the SOTA performance, and the missed detection of small objects decreased. On the other hand, ablation experiments also proved the effects of MdS, GMulW and TPA.

scholarly journals A causal relationship between face-patch activity and face-detection behavior

eLife ◽  
2017 ◽  
Vol 6 ◽  
Author(s):  
Srivatsun Sadagopan ◽  
Wilbert Zarco ◽  
Winrich A Freiwald
Keyword(s):  
Object Detection ◽  
Causal Relationship ◽  
Face Detection ◽  
Real World ◽  
Face Processing ◽  
Detection Task ◽  
Natural Scenes ◽  
Critical Importance ◽  
Primate Brain

The primate brain contains distinct areas densely populated by face-selective neurons. One of these, face-patch ML, contains neurons selective for contrast relationships between face parts. Such contrast-relationships can serve as powerful heuristics for face detection. However, it is unknown whether neurons with such selectivity actually support face-detection behavior. Here, we devised a naturalistic face-detection task and combined it with fMRI-guided pharmacological inactivation of ML to test whether ML is of critical importance for real-world face detection. We found that inactivation of ML impairs face detection. The effect was anatomically specific, as inactivation of areas outside ML did not affect face detection, and it was categorically specific, as inactivation of ML impaired face detection while sparing body and object detection. These results establish that ML function is crucial for detection of faces in natural scenes, performing a critical first step on which other face processing operations can build.

Backbone Network for Object Detection Task

2020 ◽  
Vol 57 (4) ◽  
pp. 041021
Author(s):  
宋雅麟 Song Yalin ◽  
庞彦伟 Pang Yanwei
Keyword(s):  
Object Detection ◽  
Detection Task ◽  
Backbone Network

scholarly journals Generating Images with Physics-Based Rendering for an Industrial Object Detection Task: Realism versus Domain Randomization

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7901
Author(s):  
Leon Eversberg ◽  
Jens Lambrecht
Keyword(s):  
Object Detection ◽  
Real World ◽  
Domain Knowledge ◽  
Industrial Applications ◽  
Detection Task ◽  
Training Data ◽  
Industrial Object ◽  
Versus Domain ◽  
Promising Solution ◽  
Background Object

Limited training data is one of the biggest challenges in the industrial application of deep learning. Generating synthetic training images is a promising solution in computer vision; however, minimizing the domain gap between synthetic and real-world images remains a problem. Therefore, based on a real-world application, we explored the generation of images with physics-based rendering for an industrial object detection task. Setting up the render engine’s environment requires a lot of choices and parameters. One fundamental question is whether to apply the concept of domain randomization or use domain knowledge to try and achieve photorealism. To answer this question, we compared different strategies for setting up lighting, background, object texture, additional foreground objects and bounding box computation in a data-centric approach. We compared the resulting average precision from generated images with different levels of realism and variability. In conclusion, we found that domain randomization is a viable strategy for the detection of industrial objects. However, domain knowledge can be used for object-related aspects to improve detection performance. Based on our results, we provide guidelines and an open-source tool for the generation of synthetic images for new industrial applications.

Sign in / Sign up

Export Citation Format

Share Document