scholarly journals Robust Pan/Tilt Compensation for Foreground–Background Segmentation

Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2668 ◽  
Author(s):  
Gianni Allebosch ◽  
David Van Hamme ◽  
Peter Veelaert ◽  
Wilfried Philips
Keyword(s):  
State Of The Art ◽  
Image Plane ◽  
Compensation Mechanism ◽  
Segmentation Method ◽  
Motion Models ◽  
Feature Point Extraction ◽  
Background Segmentation ◽  
Background Compensation ◽  
Camera Parameters ◽  
Robust Compensation

In this paper, we describe a robust method for compensating the panning and tilting motion of a camera, applied to foreground–background segmentation. First, the necessary internal camera parameters are determined through feature-point extraction and tracking. From these parameters, two motion models for points in the image plane are established. The first model assumes a fixed tilt angle, whereas the second model allows simultaneous pan and tilt. At runtime, these models are used to compensate for the motion of the camera in the background model. We will show that these methods provide a robust compensation mechanism and improve the foreground masks of an otherwise state-of-the-art unsupervised foreground–background segmentation method. The resulting algorithm is always able to obtain F 1 scores above 80 % on every daytime video in our test set when a minimal number of only eight feature matches are used to determine the background compensation, whereas the standard approaches need significantly more feature matches to produce similar results.

Segmentation In Medical Resonance images to extract the cancerous nodule for early diagnosis on cancer

2012 ◽  
Vol 3 (2) ◽  
pp. 253-255
Author(s):  
Raman Brar
Keyword(s):  
Human Lung ◽  
Research Work ◽  
Vital Role ◽  
Watershed Algorithm ◽  
Segmentation Method ◽  
Resonance Imaging ◽  
Segmentation Methods ◽  
Segmentation Accuracy ◽  
Background Segmentation ◽  
Lung Mri

Image segmentation plays a vital role in several medical imaging programs by assisting the delineation of physiological structures along with other parts. The objective of this research work is to segmentize human lung MRI (Medical resonance Imaging) images for early detection of cancer.Watershed Transform Technique is implemented as the Segmentation method in this work. Some comparative experiments using both directly applied watershed algorithm and after marking foreground and computed background segmentation methods show the improved lung segmentation accuracy in some image cases.

scholarly journals A Multiscale CNN-CRF Framework for Environmental Microorganism Image Segmentation

2020 ◽  
Vol 2020 ◽  
pp. 1-27
Author(s):  
Jinghua Zhang ◽  
Chen Li ◽  
Frank Kulwa ◽  
Xin Zhao ◽  
Changhao Sun ◽  
...  
Keyword(s):  
Image Segmentation ◽  
State Of The Art ◽  
Conditional Random Field ◽  
Segmentation Method ◽  
Recall Accuracy ◽  
Evaluation Indexes ◽  
Segmentation Quality ◽  
Segmentation Approach ◽  
Overall Evaluation

To assist researchers to identify Environmental Microorganisms (EMs) effectively, a Multiscale CNN-CRF (MSCC) framework for the EM image segmentation is proposed in this paper. There are two parts in this framework: The first is a novel pixel-level segmentation approach, using a newly introduced Convolutional Neural Network (CNN), namely, “mU-Net-B3”, with a dense Conditional Random Field (CRF) postprocessing. The second is a VGG-16 based patch-level segmentation method with a novel “buffer” strategy, which further improves the segmentation quality of the details of the EMs. In the experiment, compared with the state-of-the-art methods on 420 EM images, the proposed MSCC method reduces the memory requirement from 355 MB to 103 MB, improves the overall evaluation indexes (Dice, Jaccard, Recall, Accuracy) from 85.24%, 77.42%, 82.27%, and 96.76% to 87.13%, 79.74%, 87.12%, and 96.91%, respectively, and reduces the volume overlap error from 22.58% to 20.26%. Therefore, the MSCC method shows great potential in the EM segmentation field.

Improving 3-D Variational Stereo Reconstruction of Oceanic Sea States by Camera Calibration Refinement

2013 ◽  
Author(s):  
Ping-Chang Shih ◽  
Guillermo Gallego ◽  
Anthony Yezzi ◽  
Francesco Fedele
Keyword(s):  
Error Function ◽  
Image Plane ◽  
Ocean Surface ◽  
Ocean Waves ◽  
Breaking Waves ◽  
Wave Climate ◽  
Climate Extreme ◽  
Projection Model ◽  
Refinement Procedure ◽  
Camera Parameters

Studies of wave climate, extreme ocean events, turbulence, and the energy dissipation of breaking and non-breaking waves are closely related to the measurements of the ocean surface. To gauge and analyze ocean waves on a computer, we reconstruct their 3-D model by utilizing the concepts of stereoscopic reconstruction and variational optimization. This technique requires a pair of calibrated cameras — cameras whose parameters are estimated for the mathematical projection model from space to an image plane — to take videos of the ocean surface as input. However, the accuracy of camera parameters, including the orientations and the positions of cameras as well as the internal specifications of optics elements, are subject to environmental factors and manual calibration errors. Because the errors of camera parameters magnify the errors of the 3-D reconstruction after projection, we propose a novel algorithm that refines camera parameters, thereby improving the accuracy of variational 3-D reconstruction. We design a multivariate error function that represents discrepancies between captured images and the reprojection of the reconstruction onto the images. As a result of the iteratively diminished error function, the camera parameters and the reconstruction of ocean waves evolve to optimal values. We demonstrate the success of our algorithm by comparing the reconstruction results with the refinement procedure to those without it and show improvements in the statistics and spectrum of the wave reconstruction after the refinement procedure.

scholarly journals Skin Lesion Segmentation using Deep Hypercolumn Descriptors

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
Dhanesh Ramachandram ◽  
Graham W. Taylor
Keyword(s):  
Image Segmentation ◽  
Skin Lesion ◽  
State Of The Art ◽  
Jaccard Index ◽  
Segmentation Method ◽  
Lesion Segmentation ◽  
Malignant Skin

We present a image segmentation method based on deep hypercolumndescriptors which produces state-of-the-art results for thesegmentation of several classes of benign and malignant skin lesions.We achieve a Jaccard index of 0.792 on the 2017 ISIC SkinLesion Segmentation Challenge dataset.

scholarly journals Segmentation of Overlapping Cervical Cells with Mask Region Convolutional Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Jiajia Chen ◽  
Baocan Zhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
State Of The Art ◽  
Cytological Analysis ◽  
Segmentation Method ◽  
Challenging Tasks ◽  
Diagnostic Technology ◽  
Cervical Cells ◽  
Bounding Boxes

The task of segmenting cytoplasm in cytology images is one of the most challenging tasks in cervix cytological analysis due to the presence of fuzzy and highly overlapping cells. Deep learning-based diagnostic technology has proven to be effective in segmenting complex medical images. We present a two-stage framework based on Mask RCNN to automatically segment overlapping cells. In stage one, candidate cytoplasm bounding boxes are proposed. In stage two, pixel-to-pixel alignment is used to refine the boundary and category classification is also presented. The performance of the proposed method is evaluated on publicly available datasets from ISBI 2014 and 2015. The experimental results demonstrate that our method outperforms other state-of-the-art approaches with DSC 0.92 and FPRp 0.0008 at the DSC threshold of 0.8. Those results indicate that our Mask RCNN-based segmentation method could be effective in cytological analysis.

scholarly journals EmbedMask: Embedding Coupling for Instance Segmentation

2021 ◽  
Author(s):  
Hui Ying ◽  
Zhaojin Huang ◽  
Shu Liu ◽  
Tianjia Shao ◽  
Kun Zhou
Keyword(s):  
High Resolution ◽  
High Speed ◽  
State Of The Art ◽  
The State ◽  
Single Stage ◽  
Segmentation Method ◽  
Two Stage ◽  
Object Proposal ◽  
Segmentation Methods ◽  
Instance Segmentation

Current instance segmentation methods can be categorized into segmentation-based methods and proposal-based methods. The former performs segmentation first and then does clustering, while the latter detects objects first and then predicts the mask for each object proposal. In this work, we propose a single-stage method, named EmbedMask, that unifies both methods by taking their advantages, so it can achieve good performance in instance segmentation and produce high-resolution masks in a high speed. EmbedMask introduces two newly defined embeddings for mask prediction, which are pixel embedding and proposal embedding. During training, we enforce the pixel embedding to be close to its coupled proposal embedding if they belong to the same instance. During inference, pixels are assigned to the mask of the proposal if their embeddings are similar. This mechanism brings several benefits. First, the pixel-level clustering enables EmbedMask to generate high-resolution masks and avoids the complicated two-stage mask prediction. Second, the existence of proposal embedding simplifies and strengthens the clustering procedure, so our method can achieve high speed and better performance than segmentation-based methods. Without any bell or whistle, EmbedMask outperforms the state-of-the-art instance segmentation method Mask R-CNN on the challenging COCO dataset, obtaining more detailed masks at a higher speed.

Cascaded Deeply Supervised Convolutional Networks for Liver Lesion Segmentation

2021 ◽  
pp. 2152014
Author(s):  
Kaiyi Peng ◽  
Bin Fang ◽  
Mingliang Zhou
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Prediction Accuracy ◽  
Deep Neural Networks ◽  
Small Volume ◽  
State Of The Art ◽  
Liver Lesion ◽  
Segmentation Method ◽  
Lesion Segmentation ◽  
Convolutional Networks

Liver lesion segmentation from abdomen computed tomography (CT) with deep neural networks remains challenging due to the small volume and the unclear boundary. To effectively tackle these problems, in this paper, we propose a cascaded deeply supervised convolutional networks (CDS-Net). The cascaded deep supervision (CDS) mechanism uses auxiliary losses to construct a cascaded segmentation method in a single network, focusing the network attention on pixels that are more difficult to classify, so that the network can segment the lesion more effectively. CDS mechanism can be easily integrated into standard CNN models and it helps to increase the model sensitivity and prediction accuracy. Based on CDS mechanism, we propose a cascaded deep supervised ResUNet, which is an end-to-end liver lesion segmentation network. We conduct experiments on LiTS and 3DIRCADb dataset. Our method has achieved competitive results compared with other state-of-the-art ones.

QuadrupletNet: A Novel Local Descriptor for Brain Tumor Detection and Segmentation

2020 ◽  
Vol 10 (7) ◽  
pp. 1763-1768
Author(s):  
Jun Jiang ◽  
Jing Jin ◽  
Binluo Wang ◽  
Jinming Wang ◽  
Tiaojuan Ren ◽  
...  
Keyword(s):  
Brain Tumor ◽  
State Of The Art ◽  
Tumor Detection ◽  
Segmentation Method ◽  
Resonance Imaging ◽  
Brain Tumor Surgery ◽  
Local Descriptor ◽  
Mri Brain ◽  
Triplet Loss ◽  
Magnetic Resonance Imaging Mri

Brain tumor detection and segmentation from Magnetic Resonance Imaging (MRI) images is being one of the emerging fields in the biomedicine. A formidable undertaking in brain tumor surgery, medical care, treatment programme and quantitative assessment of MRI images is to precisely diagnose its location and extent. Recently, the convolutional neural network (CNN) based detection and segmentation method on brain tumor MRI images is being one of the emerging fields in the medical imaging as an automatic clinic treatment and evaluation solution. In this article, we put forward a brand new quadruplet loss in CNN framework, which achieves higher accuracy in brain tumor detection and segmentation than other pairwise loss and triplet loss methods. By applying the proposed quadruplet loss to the original L2Net CNN architecture leads to a more compact descriptor named QuadrupletNet. From our experiments, QuadrupletNet shows higher performance than other state-of-the-art loss functions e.g., the Triplet loss, as indicated in experiments on Multimodal Brain Tumor Image Segmentation (BRATS 2018) datasets, and on our own collected MRI brain tumor datasets (named MBTD).

Sign in / Sign up

Export Citation Format

Share Document