Automatic Biological Cell Counting Using a Modified Gradient Hough Transform

Denimal, Emmanuel; Marin, Ambroise; Guyot, Stéphane; Journaux, Ludovic; Molin, Paul

doi:10.1017/s1431927616012617

Cited by 4 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the overall structure, target counting methods can be divided into those based on traditional feature extraction (Zhou et al, 2014;Denimal et al, 2017;Li et al, 2020) and those based on the convolutional neural network (CNN) (Yoo et al, 2016;He et al, 2017;Redmon and Farhadi, 2018). Traditional feature extraction methods include the Haar-like feature, the local binary pattern, and histogram of the oriented gradient.…”

Section: Dcn-multinet-yolomentioning

confidence: 99%

A Deep Learning–Based Approach for Moving Vehicle Counting and Short-Term Traffic Prediction From Video Images

Zheng

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

The intelligent transportation system (ITS) is one of the effective solutions to the problem of urban traffic congestion, and it is also one of the important topics of smart city construction. One particular application is the traffic monitoring and flow prediction. However, there are still challenges regarding both aspects. On the one hand, the current traffic monitoring relies heavily on the single object detection method that cannot achieve accurate statistics of moving target counting and, meanwhile, has limited speed advantage; on the other hand, the existing traffic flow prediction models rarely consider different weather conditions. Therefore, the present article attempts to propose a packaged solution, which combines a new target tracking and moving vehicle counting method and an improved long short-term memory (LSTM) network for traffic flow forecast with weather conditions. More specifically, the DCN V2 convolution kernel and MultiNetV3 framework are used to replace YOLOv4’s conventional convolution kernel and backbone network to realize multi-target tracking and counting, respectively. Subsequently, combined with the temporal characteristics of historical traffic flow, this article introduces weather conditions into the LSTM network and realizes the short-term prediction of traffic flow at the road junction level. This study carries out a series of experiments using the real traffic video data with a 2-month time span at a popular road junction in the downtown of Shenzhen, China. The results suggest that the proposed algorithms outperform the previous methods in terms of the 10% higher accuracy of target detection tracking and about a half reduction of traffic prediction error, when considering weather conditions.

show abstract

Section: Dcn-multinet-yolomentioning

confidence: 99%

A Deep Learning–Based Approach for Moving Vehicle Counting and Short-Term Traffic Prediction From Video Images

Zheng

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…Actually, it forces the biologist to manually set some parameters for a group of images preventing its automation just as here, where the images have to be separated in classes and few parameters fixed to limit the computational time but preventing a full automation. Recently, few authors proposed new solutions such as using gradient accumulation matrix (Denimal et al 2017) or color variation detections by a computer vision system to improve the automation potential (Murillo-Bracamontes et al 2012). Those solutions are currently investigated for an application on aerial jellyfish proliferation captured by drone as shown on Figure 5.…”

Section: Implementation Of Hough Transform In Biologymentioning

confidence: 99%

Hough transform implementation to evaluate the morphological variability of the moon jellyfish (Aureliaspp.)

Lacaux

Desolneux²,

Gadreaud

et al. 2020

Preprint

View full text Add to dashboard Cite

13Variations of the animal body plan morphology and morphometry can be used as prognostic 14 tools of their habitat quality. The potential of the moon jellyfish (Aurelia spp.) as a new model 15 organism has been poorly tested. However, as a tetramerous symmetry organism, it exhibits 16 some variations in radial symmetry number. A pertinent list of morphologicalnumber of 17 gonadsand morphometric characteristicse.g. ratio of the gonads area on the umbrella area -18 has been established to describe the morphology of 19 specimens through an image analysis. 19The method uses for the first time the Hough transform to approximate the gonads and the 20 umbrella by ellipses and automatically extracts the morphometric data. The results highlight 21 two discriminant parameters: distance between the center of the gonads and the center of the 22 umbrella, and the individual variability of the gonad eccentricity, both higher in jellyfishes with 23 5 gonads. Additionally, the relative size of the gonads is not different between tetramerous and 24 non-tetramerous jellyfishes bringing some hypothesis about fitness advantages or 25 disadvantages. Combined to ecotoxicological bioassays to better understand the causes of this 26 developmental alteration, this optimizable method can become a powerful tool in the symmetry 27 description of an in situ population. 28Keywords Jellyfish · Morphometry · Symmetry disorder · Hough transform 29

show abstract

“…In a previous paper (Denimal et al, 2017), we developed methods for cell counting based on accumulation algorithms. Unfortunately, it does not allow for RNPs counting because these objects are defined by a very low number of pixels and do not allow for a sufficient accumulation.…”

Section: Introductionmentioning

confidence: 99%

Automatic Counting of Intra-Cellular Ribonucleo-Protein Aggregates inSaccharomyces cerevisiaeUsing a Textural Approach

Marin¹,

Denimal²,

Bertheau³

et al. 2019

Microsc Microanal

Self Cite

View full text Add to dashboard Cite

In the context of microbiology, recent studies show the importance of ribonucleo-protein aggregates (RNPs) for the understanding of mechanisms involved in cell responses to specific environmental conditions. The assembly and disassembly of aggregates is a dynamic process, the characterization of the stage of their evolution can be performed by the evaluation of their number. The aim of this study is to propose a method to automatically determine the count of RNPs. We show that the determination of a precise count is an issue by itself and hence, we propose three textural approaches: a classical point of view using Haralick features, a frequency point of view with generalized Fourier descriptors, and a structural point of view with Zernike moment descriptors (ZMD). These parameters are then used as inputs for a supervised classification in order to determine the most relevant. An experiment using a specific Saccharomyces cerevisiae strain presenting a fusion between a protein found in RNPs (PAB1) and the green fluorescent protein was performed to benchmark this approach. The fluorescence was observed with two-photon fluorescence microscopy. Results show that the textural approach, by mixing ZMD with Haralick features, allows for the characterization of the number of RNPs.

show abstract

Automatic Biological Cell Counting Using a Modified Gradient Hough Transform

Cited by 4 publications

References 14 publications

A Deep Learning–Based Approach for Moving Vehicle Counting and Short-Term Traffic Prediction From Video Images

A Deep Learning–Based Approach for Moving Vehicle Counting and Short-Term Traffic Prediction From Video Images

Hough transform implementation to evaluate the morphological variability of the moon jellyfish (Aureliaspp.)

Automatic Counting of Intra-Cellular Ribonucleo-Protein Aggregates inSaccharomyces cerevisiaeUsing a Textural Approach

Contact Info

Product

Resources

About