More Like this

1. Erroneous pixel prediction for semantic image segmentation

   https://doi.org/10.1007/s41095-021-0235-7  

   Gong, Lixue; Zhang, Yiqun; Zhang, Yunke; Yang, Yin; Xu, Weiwei (March 2022, Computational Visual Media)

   Abstract We consider semantic image segmentation. Our method is inspired by Bayesian deep learning which improves image segmentation accuracy by modeling the uncertainty of the network output. In contrast to uncertainty, our method directly learns to predict the erroneous pixels of a segmentation network, which is modeled as a binary classification problem. It can speed up training comparing to the Monte Carlo integration often used in Bayesian deep learning. It also allows us to train a branch to correct the labels of erroneous pixels. Our method consists of three stages: (i) predict pixel-wise error probability of the initial result, (ii) redetermine new labels for pixels with high error probability, and (iii) fuse the initial result and the redetermined result with respect to the error probability. We formulate the error-pixel prediction problem as a classification task and employ an error-prediction branch in the network to predict pixel-wise error probabilities. We also introduce a detail branch to focus the training process on the erroneous pixels. We have experimentally validated our method on the Cityscapes and ADE20K datasets. Our model can be easily added to various advanced segmentation networks to improve their performance. Taking DeepLabv3+ as an example, our network can achieve 82.88% of mIoU on Cityscapes testing dataset and 45.73% on ADE20K validation dataset, improving corresponding DeepLabv3+ results by 0.74% and 0.13% respectively. 

   more » « less
2. Cotton Yield Estimation From Aerial Imagery Using Machine Learning Approaches

   https://doi.org/10.3389/fpls.2022.870181  

   Rodriguez-Sanchez, Javier; Li, Changying; Paterson, Andrew H (April 2022, Frontiers in Plant Science)

   Estimation of cotton yield before harvest offers many benefits to breeding programs, researchers and producers. Remote sensing enables efficient and consistent estimation of cotton yields, as opposed to traditional field measurements and surveys. The overall goal of this study was to develop a data processing pipeline to perform fast and accurate pre-harvest yield predictions of cotton breeding fields from aerial imagery using machine learning techniques. By using only a single plot image extracted from an orthomosaic map, a Support Vector Machine (SVM) classifier with four selected features was trained to identify the cotton pixels present in each plot image. The SVM classifier achieved an accuracy of 89%, a precision of 86%, a recall of 75%, and an F1-score of 80% at recognizing cotton pixels. After performing morphological image processing operations and applying a connected components algorithm, the classified cotton pixels were clustered to predict the number of cotton bolls at the plot level. Our model fitted the ground truth counts with anR²value of 0.93, a normalized root mean squared error of 0.07, and a mean absolute percentage error of 13.7%. This study demonstrates that aerial imagery with machine learning techniques can be a reliable, efficient, and effective tool for pre-harvest cotton yield prediction. 

   more » « less
3. Automated, high-throughput image calibration for parallel-laser photogrammetry

   https://doi.org/10.1007/s42991-021-00174-7  

   Richardson, Jack L.; Levy, Emily J.; Ranjithkumar, Riddhi; Yang, Huichun; Monson, Eric; Cronin, Arthur; Galbany, Jordi; Robbins, Martha M.; Alberts, Susan C.; Reeves, Mark E.; et al (March 2022, Mammalian Biology)

   Parallel-laser photogrammetry is growing in popularity as a way to collect non-invasive body size data from wild mammals. Despite its many appeals, this method requires researchers to hand-measure (i) the pixel distance between the parallel laser spots (inter-laser distance) to produce a scale within the image, and (ii) the pixel distance between the study subject’s body landmarks (inter-landmark distance). This manual effort is time-consuming and introduces human error: a researcher measuring the same image twice will rarely return the same values both times (resulting in within-observer error), as is also the case when two researchers measure the same image (resulting in between-observer error). Here, we present two independent methods that automate the inter-laser distance measurement of parallel-laser photogrammetry images. One method uses machine learning and image processing techniques in Python, and the other uses image processing techniques in ImageJ. Both of these methods reduce labor and increase precision without sacrificing accuracy. We first introduce the workflow of the two methods. Then, using two parallel-laser datasets of wild mountain gorilla and wild savannah baboon images, we validate the precision of these two automated methods relative to manual measurements and to each other. We also estimate the reduction of variation in final body size estimates in centimeters when adopting these automated methods, as these methods have no human error. Finally, we highlight the strengths of each method, suggest best practices for adopting either of them, and propose future directions for the automation of parallel-laser photogrammetry data. 

   more » « less
4. Structure-Aware Image Segmentation with Homotopy Warping

   Hu, Xiaoling (December 2022, The Thirty-sixth Conference on Neural Information Processing Systems)

   Besides per-pixel accuracy, topological correctness is also crucial for the segmentation of images with fine-scale structures, e.g., satellite images and biomedical images. In this paper, by leveraging the theory of digital topology, we identify pixels in an image that are critical for topology. By focusing on these critical pixels, we propose a new homotopy warping loss to train deep image segmentation networks for better topological accuracy. To efficiently identify these topologically critical pixels, we propose a new algorithm exploiting the distance transform. The proposed algorithm, as well as the loss function, naturally generalize to different topological structures in both 2D and 3D settings. The proposed loss function helps deep nets achieve better performance in terms of topology-aware metrics, outperforming state-of-the-art structure/topology-aware segmentation methods. 

   more » « less
5. Calibrated bagging deep learning for image semantic segmentation: A case study on COVID-19 chest X-ray image

   https://doi.org/10.1371/journal.pone.0276250  

   Nwosu, Lucy; Li, Xiangfang; Qian, Lijun; Kim, Seungchan; Dong, Xishuang (November 2022, PLOS ONE)

   Hemanth, Jude (Ed.)

   Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). Imaging tests such as chest X-ray (CXR) and computed tomography (CT) can provide useful information to clinical staff for facilitating a diagnosis of COVID-19 in a more efficient and comprehensive manner. As a breakthrough of artificial intelligence (AI), deep learning has been applied to perform COVID-19 infection region segmentation and disease classification by analyzing CXR and CT data. However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated. In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty. The proposed method has been validated on a large dataset that is associated with CXR image segmentation. Experimental results demonstrate that the proposed method can improve the segmentation performance, as well as decrease prediction uncertainty. 

   more » « less