scholarly journals Parallel Fish School Tracking Based on Multiple Appearance Feature Detection

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3476
Author(s):  
Zhitao Wang ◽  
Chunlei Xia ◽  
Jangmyung Lee
Keyword(s):  
Feature Detection ◽  
Model Organism ◽  
Correct Identification ◽  
Trajectory Data ◽  
Detection Scheme ◽  
Fish School ◽  
Movement Trajectories ◽  
School Tracking ◽  
Fish Detection ◽  
Appearance Feature

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.

scholarly journals An Image Copy-Move Forgery Detection Scheme Based on A-KAZE and SURF Features

Symmetry ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 706 ◽  
Author(s):  
Chengyou Wang ◽  
Zhi Zhang ◽  
Xiao Zhou
Keyword(s):  
Feature Detection ◽  
Joint Photographic Expert Group ◽  
Social Stability ◽  
Forgery Detection ◽  
Detection Scheme ◽  
Speeded Up Robust Features ◽  
Image Blurring ◽  
Surf Features ◽  
Copy Move Forgery Detection ◽  
Processing Techniques

The popularity of image editing software has made it increasingly easy to alter the content of images. These alterations threaten the authenticity and integrity of images, causing misjudgments and possibly even affecting social stability. The copy-move technique is one of the most commonly used approaches for manipulating images. As a defense, the image forensics technique has become popular for judging whether a picture has been tampered with via copy-move, splicing, or other forgery techniques. In this paper, a scheme based on accelerated-KAZE (A-KAZE) and speeded-up robust features (SURF) is proposed for image copy-move forgery detection (CMFD). It is difficult for most keypoint-based CMFD methods to obtain sufficient points in smooth regions. To remedy this defect, the response thresholds for the A-KAZE and SURF feature detection stages are set to small values in the proposed method. In addition, a new correlation coefficient map is presented, in which the duplicated regions are demarcated, combining filtering and mathematical morphology operations. Numerous experiments are conducted to demonstrate the effectiveness of the proposed method in searching for duplicated regions and its robustness against distortions and post-processing techniques, such as noise addition, rotation, scaling, image blurring, joint photographic expert group (JPEG) compression, and hybrid image manipulation. The experimental results demonstrate that the performance of the proposed scheme is superior to that of other tested CMFD methods.

scholarly journals Using Convolutional Neural Networks for Detection and Morphometric Analysis of Carolina Bays from Publicly Available Digital Elevation Models

2021 ◽  
Vol 13 (18) ◽  
pp. 3770
Author(s):  
Mark A. Lundine ◽  
Arthur C. Trembanis
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Feature Detection ◽  
Digital Elevation Models ◽  
Open Water ◽  
Atlantic Coastal Plain ◽  
Detection Scheme ◽  
Carolina Bays ◽  
Digital Elevation ◽  
Almost All

Carolina Bays are oriented and sandy-rimmed depressions that are ubiquitous throughout the Atlantic Coastal Plain (ACP). Their origin has been a highly debated topic since the 1800s and remains unsolved. Past population estimates of Carolina Bays have varied vastly, ranging between as few as 10,000 to as many as 500,000. With such a large uncertainty around the actual population size, mapping these enigmatic features is a problem that requires an automated detection scheme. Using publicly available LiDAR-derived digital elevation models (DEMs) of the ACP as training images, various types of convolutional neural networks (CNNs) were trained to detect Carolina bays. The detection results were assessed for accuracy and scalability, as well as analyzed for various morphologic, land-use and land cover, and hydrologic characteristics. Overall, the detector found over 23,000 Carolina Bays from southern New Jersey to northern Florida, with highest densities along interfluves. Carolina Bays in Delmarva were found to be smaller and shallower than Bays in the southeastern ACP. At least a third of Carolina Bays have been converted to agricultural lands and almost half of all Carolina Bays are forested. Few Carolina Bays are classified as open water basins, yet almost all of the detected Bays were within 2 km of a water body. In addition, field investigations based upon detection results were performed to describe the sedimentology of Carolina Bays. Sedimentological investigations showed that Bays typically have 1.5 m to 2.5 m thick sand rims that show a gradient in texture, with coarser sand at the bottom and finer sand and silt towards the top. Their basins were found to be 0.5 m to 2 m thick and showed a mix of clayey, silty, and sandy deposits. Last, the results compiled during this study were compared to similar depressional features (i.e., playa-lunette systems) to pinpoint any similarities in origin processes. Altogether, this study shows that CNNs are valuable tools for automated geomorphic feature detection and can lead to new insights when coupled with various forms of remotely sensed and field-based datasets.

scholarly journals The interplay between movement, dispersal and morphology in Tetrahymena ciliates

2018 ◽  
Author(s):  
Frank Pennekamp ◽  
Jean Clobert ◽  
Nicolas Schtickzelle
Keyword(s):  
Model Organism ◽  
Spatial Location ◽  
Morphological Properties ◽  
Movement Speed ◽  
Movement Behaviour ◽  
Dispersal Rate ◽  
Movement Trajectories ◽  
Spatio Temporal ◽  
Path Tortuosity

Understanding how and why individual movement translates into dispersal between populations is a long-term goal in ecology. Movement is broadly defined as “any change in the spatial location of an individual”, whereas dispersal is more narrowly defined as a movement that may lead to gene flow. Because the former may create the condition for the latter, behavioural decisions that lead to dispersal may be detectable in underlying movement behaviour. In addition, dispersing individuals also have specific sets of morphological and behavioural traits that help them coping with the costs of movement and dispersal, and traits that mitigate costs should be under selection and evolve if they have a genetic basis. Here we experimentally study the relationships between movement behaviour, morphology and dispersal across 44 genotypes of the actively dispersing unicellular, aquatic model organism Tetrahymena thermophila. We used two-patch populations to quantify individual movement trajectories, as well as activity, morphology and dispersal rate. First, we studied variation in movement behaviour among and within genotypes (i.e. between dispersers and residents) and tested whether this variation can be explained by morphology. Then, we address how much the dispersal rate is driven by differences in the underlying movement behaviour. Genotypes expressed different movements in terms of speed and path tortuosity. We also detected marked movement differences between resident and dispersing individuals, mediated by the genotype. Movement variation was partly explained by morphological properties such as cell size and shape, with larger cells consistently showing higher movement speed and lower tortuosity. Genetic differences in activity and diffusion rates were positively related to the observed dispersal and jointly explained 45% of the variation in dispersal rate. Our study shows that a detailed understanding of the interplay between morphology, movement and dispersal may have potential to improve dispersal predictions over broader spatio-temporal scales.

scholarly journals A Trajectory Partition Method Based on Combined Movement Features

2019 ◽  
Vol 2019 ◽  
pp. 1-13 ◽  
Author(s):  
Ji Tang ◽  
Linfeng Liu ◽  
Jiagao Wu
Keyword(s):  
Data Mining ◽  
Change Points ◽  
Feature Points ◽  
Trajectory Data ◽  
Trade Off ◽  
Movement Trajectories ◽  
Trajectory Data Mining ◽  
Primary Procedure ◽  
Simulation Results ◽  
Partition Method

Trajectory data mining has become an increasing concern in the location-based applications, and the trajectory partition is taken as the primary procedure of trajectory data mining. The amount of movement trajectories of nodes is typically very large, and the trajectory shapes are extremely diverse, which makes the trajectory partition a vital issue to the trajectory data mining results. In this work, the movement behaviors of nodes are analyzed from the aspects of moving speeds, stop points, and moving directions, and then a novel Trajectory Partition Method based on combined movement Features (TPMF) is proposed to partition the trajectories. In TPMF, we first extract the change points where the movement speeds of nodes are varied significantly; then, we extract the stop points by detecting the speed variations of nodes; finally, the Douglas-Peucker algorithm is applied to partition the subtrajectories according to the extracted feature points (change points and stop points). Simulations are carried out on the Geolife trajectory dataset, and the simulation results indicate that TPMF can achieve a preferable trade-off between the simplification rate and the trajectory partition error, while the running time is shortened as well.

scholarly journals Trip Extraction of Shared Electric Bikes Based on Multi-Rule-Constrained Homomorphic Linear Clustering Algorithm

2019 ◽  
Vol 8 (12) ◽  
pp. 526
Author(s):  
Xiaoqian Cheng ◽  
Chengming Li ◽  
Weibing Du ◽  
Jianming Shen ◽  
Zhaoxin Dai
Keyword(s):  
Clustering Algorithm ◽  
New Method ◽  
Correct Identification ◽  
Hotspot Detection ◽  
Trajectory Data ◽  
Time Duration ◽  
Contextual Constraint ◽  
Two Factors ◽  
Directional Constraint ◽  
Electric Bike

Trajectory data include rich interactive information of humans. The correct identification of trips is the key to trajectory data mining and its application. A new method, multi-rule-constrained homomorphic linear clustering (MCHLC), is proposed to extract trips from raw trajectory data. From the perspective of the workflow, the MCHLC algorithm consists of three parts. The first part is to form the original sub-trajectory moving/stopping clusters, which are obtained by sequentially clustering trajectory elements of the same motion status. The second part is to determine and revise the motion status of the original sub-trajectory clusters by the speed, time duration, directional constraint, and contextual constraint to construct the stop/move model. The third part is to extract users’ trips by filtering the stop/move model using the following rules: distance rule, average speed rule, shortest path rule, and completeness rule, which are related to daily riding experiences. Verification of the new method is carried out with the shared electric bike trajectory data of one week in Tengzhou city, evaluated by three indexes (precision, recall, and F1-score). The experiment shows that the index values of the new algorithm are higher (above 93%) than those of the baseline methods, indicating that the new algorithm is better. Compared to the baseline velocity sequence linear clustering (VSLC) algorithm, the performance of the new algorithm is improved by approximately 10%, mainly owing to two factors, directional constraint and contextual constraint. The better experimental results indicate that the new algorithm is suitable to extract trips from the sparse trajectories of shared e-bikes and other transportation forms, which can provide technical support for urban hotspot detection and hot route identification.

Sign in / Sign up

Export Citation Format

Share Document