Convolutional neural network-based coarse initial position estimation of a monocular camera in large-scale 3D light detection and ranging maps

Sun, Manhui; Yang, Shaowu; Liu, Hengzhu

doi:10.1177/1729881419893518

Cited by 5 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method learns the cross-domain features through a weighted soft-margin triplet loss, while ignoring the underlying geometry connections between the two different domains. Sun et.al [11] introduce an image-to-range coarse localization method by building the feature connections within depth images, where the depth is estimated from a depth prediction network.…”

Section: Related Workmentioning

confidence: 99%

i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

Yin¹,

Xu²,

Ji³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a method for localizing a single camera with respect to a point cloud map in indoor and outdoor scenes. The problem is challenging because correspondences of local invariant features are inconsistent across the domains between image and 3D. The problem is even more challenging as the method must handle various environmental conditions such as illumination, weather, and seasonal changes. Our method can match equirectangular images to the 3D range projections by extracting cross-domain symmetric place descriptors. Our key insight is to retain condition-invariant 3D geometry features from limited data samples while eliminating the condition-related features by a designed Generative Adversarial Network. Based on such features, we further design a spherical convolution network to learn viewpoint-invariant symmetric place descriptors. We evaluate our method on extensive self-collected datasets, which involve Long-term (variant appearance conditions), Large-scale (up to 2km structure/unstructured environment), and Multistory (four-floor confined space). Our method surpasses other current state-of-the-arts by achieving around 3 times higher place retrievals to inconsistent environments, and above 3 times accuracy on online localization. To highlight our method's generalization capabilities, we also evaluate the recognition across different datasets. With a single trained model, i3dLoc can demonstrate reliable visual localization in random conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

Yin¹,

Xu²,

Ji³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the precision-recall curve evaluation index, precision ¼ TP/(TPþFP) indicates the probability that the prediction is correct in the positive sample, and recall ¼ TP/(TPþFN) indicates the probability that the prediction is correct in the actual positive sample. 18 The more the precision-recall curve of a classifier in the plane rectangular coordinate system is convex to the upper right, indicating that the performance of this classifier is better. In addition, since the precision-recall curve is affected by the test sample, there will be a large fluctuation of the curve, so the AveP is generally used to measure the performance of the classifier.…”

Section: Experiments Processmentioning

confidence: 99%

A novel image edge smoothing method based on convolutional neural network

2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

In the field of visual perception, the edges of images tend to be rich in effective visual stimuli, which contribute to the neural network’s understanding of various scenes. Image smoothing is an image processing method used to highlight the wide area, low-frequency components, main part of the image or to suppress image noise and high-frequency interference components, which could make the image’s brightness smooth and gradual, reduce the abrupt gradient, and improve the image quality. At present, there are still problems such as easy blurring of the edges of the image, poor overall smoothing effect, obvious step effect, and lack of robustness to noise on image smoothing. Based on the convolutional neural network, this article proposes a method for edge detection and deep learning for image smoothing. The results show that the research method proposed in this article solves the problem of edge detection and information capture better, significantly improves the edge effect, and protects the effectiveness of edge information. At the same time, it reduces the signal-to-noise ratio of the smoothed image and greatly improves the effect of image smoothing.

show abstract

“…Compared with traditional LDI, multiview LDI (MVLDI) creates fewer layers and eliminates more redundancy. In references [35,36], the author proposes a novel method that uses a convolutional neural network to enable a mobile robot to estimate its rough position in a 3D map using only a monocular camera. e article uses a pretrained convolutional neural network model to generate a depth image descriptor, and retrieves the location by calculating the similarity score between the current depth image and the depth image projected from the 3D map.…”

Section: Introductionmentioning

confidence: 99%

Swimmer’s Posture Recognition and Correction Method Based on Embedded Depth Image Skeleton Tracking

Wang

Junhua

Luo

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the continuous emergence of depth image recognition technology, human motion recognition technology has gradually come to life. However, because the current technology of image recognition and skeletal tracking is too backward, people cannot use gesture recognition robots to perform gesture recognition and correction with high accuracy for athletes. In this study, the skeletal tracking depth image is obtained through the Kinect sensor. When using the Kinect sensor to acquire images, the requirements for the environment around the measured object are very low, and it will not be affected by conditions such as light, shadow, and object occlusion, and the pose can be segmented in real time in a complex background. In this study, the depth map feature and the bone information feature are selected for fusion. The HOD feature is difficult to deal with the occlusion problem, and it is not easy to detect the excessive range of the human body gesture or the change of the object direction. Based on this, the HOD feature is improved in many places to form a new 3D-HOD feature and DMM-HOG feature. In this study, the technical research on posture recognition and correction of swimmers in the experiment has realized posture collection, posture segmentation, posture analysis, posture modeling, and posture recognition. In this study, random forests are combined with HOD features to classify pixel-by-pixel points in depth images. The accuracy of training pixel classification is as high as 85%, and the average recognition time of the decision tree for each pose is about 9% higher than that of random forests. The use of Meanshift algorithm to cluster the classified pixels to form skeletal joint points is fast and efficient, and can quickly and accurately find joint points. It has also achieved good experimental effects on human motion recognition and continuous motion recognition, is more suitable for real life, and has commercial practical value.

show abstract

Convolutional neural network-based coarse initial position estimation of a monocular camera in large-scale 3D light detection and ranging maps

Cited by 5 publications

References 34 publications

i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions

A novel image edge smoothing method based on convolutional neural network

Swimmer’s Posture Recognition and Correction Method Based on Embedded Depth Image Skeleton Tracking

Contact Info

Product

Resources

About