Dataset Information

Parallel Fish School Tracking Based on Multiple Appearance Feature Detection.

ABSTRACT: A parallel fish school tracking based on multiple-feature fish detection has been proposed in this paper to obtain accurate movement trajectories of a large number of zebrafish. Zebrafish are widely adapted in many fields as an excellent model organism. Due to the non-rigid body, similar appearance, rapid transition, and frequent occlusions, vision-based behavioral monitoring is still a challenge. A multiple appearance feature based fish detection scheme was developed by examining the fish head and center of the fish body based on shape index features. The proposed fish detection has the advantage of locating individual fishes from occlusions and estimating their motion states, which could ensure the stability of tracking multiple fishes. Moreover, a parallel tracking scheme was developed based on the SORT framework by fusing multiple features of individual fish and motion states. The proposed method was evaluated in seven video clips taken under different conditions. These videos contained various scales of fishes, different arena sizes, different frame rates, and various image resolutions. The maximal number of tracking targets reached 100 individuals. The correct tracking ratio was 98.60% to 99.86%, and the correct identification ratio ranged from 97.73% to 100%. The experimental results demonstrate that the proposed method is superior to advanced deep learning-based methods. Nevertheless, this method has real-time tracking ability, which can acquire online trajectory data without high-cost hardware configuration.

SUBMITTER: Wang Z

PROVIDER: S-EPMC8156864 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background Evaluate the predictive value of myocardial stress measured by magnetic resonance imaging (MRI) on the severity of coronary artery stenosis and acute myocardial infarction (AMI). In the early stage of acute myocardial infarction, many imaging findings are negative, and MRI myocardial stress detection is controversial in the diagnosis of this aspect. Therefore, it is necessary to determine whether MRI myocardial stress can diagnose acute myocardial infarction. Methods A total of 120 patients were divided into an AMI group and non-AMI group. The AMI group was further divided into a mild group, moderate group, and severe group. The myocardial stress was measured by MRI, compared in each group, the correlation between myocardial stress and coronary artery stenosis rate was analyzed, and coronary artery disease (CAD) compared between patients with AMI, and the relationship between myocardial stress and AMI was observed. Results Among the 120 patients, there were 77 cases in the AMI group, including 21 cases in the mild group, 40 cases in the moderate group, and 16 cases in the severe group. There were a total of 43 cases in the non-AMI group. Myocardial stress in the AMI group was significantly higher than that in the non-AMI group (P<0.05). The myocardial stress increased gradually in the mild, moderate, and severe AMI groups (P<0.001). Myocardial stress was positively correlated with coronary artery stenosis rate (P<0.001) and CAD (P<0.05). Logistic regression analysis showed that myocardial stress was an independent risk factor for AMI (P<0.05). The sensitivity and specificity of myocardial stress >5.15 mm in the diagnosis of AMI were 83.5%, 68.6% (AUC =0.834), respectively. Acute myocardial infarction is often caused by risk factors such as hyperlipidemia, hypertension and hyperglycemia, as well as vascular stenosis caused by arterial wall malformation, vascular wall inflammation or vasospasm. Conclusions The MRI measurement of myocardial stress is simple, reliable, and practical to evaluate the degree of coronary artery lesions. Myocardial stress is closely related to AMI and can assist in the diagnosis of AMI.

Dataset Information

Parallel Fish School Tracking Based on Multiple Appearance Feature Detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets