An improved K-means algorithm for underwater image background segmentation

Conventional algorithms fail to obtain satisfactory background segmentation results for underwater images. In this study, an improved K-means algorithm was developed for underwater image background segmentation to address the issue of improper K value determination and minimize the impact of initial centroid position of grayscale image during the gray level quantization of the conventional K-means algorithm. A total of 100 underwater images taken by an underwater robot were sampled to test the aforementioned algorithm in respect of background segmentation validity and time cost. The K value and initial centroid position of grayscale image were optimized. The results were compared to the other three existing algorithms, including the conventional K-means algorithm, the improved Otsu algorithm, and the Canny operator edge extraction method. The experimental results showed that the improved K-means underwater background segmentation algorithm could effectively segment the background of underwater images with a low color cast, low contrast, and blurred edges. Although its cost in time was higher than that of the other three algorithms, it none the less proved more efficient than the time-consuming manual segmentation method. The algorithm proposed in this paper could potentially be used in underwater environments for underwater background segmentation.

Dynamic Changes in Bladder Morphology Over Time in Cervical Cancer Patients

Objectives: Continuous surveillance of bladder volume (BV) is beneficial during the treatment of various urogenital diseases because the bladder is always changing its position, size and even shape at different filling phases. For this purpose, we quantified the motion of the urinary bladder. Methods: Daily ultrasound measurements and weekly cone-beam computed tomography scans were obtained from 89 patients in the supine position. BV, bladder centroid positions, and triaxial lengths in the left-right (LR), anterior-posterior (AP), and superior-inferior (SI) directions were compared across different time points. Results: BV linearly increased over time, and the mean urinary filling rate ( vtot) was correlated with the patients’ age and water consumption. The greatest bladder centroid motion occurred longitudinally, with less movement observed laterally. The maximum bladder centroid movement was 18.8 ± 2.2 mm inferiorly and 1.8 ± 0.9 mm posteriorly for every 10% decrease in BV. The rates of changes in triaxial lengths differed across the 4 filling phases. The rate was the largest at a BV range of 10-80 mL, especially in the LR direction, with values of 5.9 ± 1.0, 3.6 ± 1.0, and 3.9 ± 1.0 mm per every 10-mL BV increase for LR, AP, and SI, respectively. With bladder filling (<80 mL), the maximum increase in triaxial length was observed in the SI direction and the rates of all changes considerably decreased, especially at BV > 600 mL. Conclusion: The vtot could be used to evaluate the temporal changes in the bladder. The spatial changes should be assessed according to different filling phases based on the centroid position and triaxial lengths.

Study on the Influence of the Center of Gravity of Fuel Cell City Bus on its Handling Characteristics

The vehicles driven by combustion engine leads to environmental problems because of fossil fuel consumption. In recent years, many policies have adopted to support the development of new energy vehicles, especially battery electric vehicles as the main strategy in China. For the battery electric vehicles, the position of the battery pack can change the centroid position of the vehicle because of its big mass, and it can also change the loading of each tire in the motion, which has important influence on the vehicle handing and stability performance. This article studies the relationship between handling characteristic and the change of centroid position on a fuel cell city bus, and then solves the suitable centroid position of this vehicle which makes the vehicle have satisfied steering characteristic.

Potential of IMU-Based Systems in Measuring Single Rapid Movement Variables in Females with Different Training Backgrounds and Specialization

The aim of this paper is to determine the discriminative potential of the IMU-based system for the measurement of rapid hand movement properties, i.e., relevant kinematic variables in relation to different groups of participants. The measurement of the kinematics of the rapid hand movement was performed using a standard hand tapping test. The sample in this research included a total of 70 female participants and was divided into 3 subsamples. The discriminant analysis has identified two functions, DF1 and DF2, that explain 91.1 and 8.1% of the variance, respectively. The differences between the examined subsamples originate from the variables grouped in DF1, which were statistically significant (p≤0.000). In relation to this function, the national volleyball team centroid position was shifted with -1.108 and -1.968 standard deviation values from the control group and youth volleyball team, respectively. The difference between control and Voll_Youth groups was -0.860 standard deviation value. The factors with the greatest discriminative potential among the groups represent the temporal characteristics of the rapid hand movement, i.e., the time elapsed between the onset of the movement and the first and second tap, as defined by the variables t1 and t2, respectively. The established findings clearly indicate that IMU sensors are practically applicable in relation to the sensitive measurement of rapid arm movement capability of female athletes.

TSD-CPI: Traffic Sign Detection Technique Based on Centroid Position Identification in Text Mining

Detecting and Identifying traffic sign is a complicated issue due to the changing variability in cloud conditions. Hence, it is necessary to identify and detect of traffic signs during journey. The traffic text sign identification fails due to noise, blur, distortion and occlusion. In order to identify the text, a technique should be adapted that recognizes the text with improved accuracy. In existing algorithms such as Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) were not detecting the Centroid position. In this paper, the text Centroid of position sign is detected using text color, font and size. During journey, if the text is blurred, this Traffic Sign Detection Technique based on Centroid Position Identification (TSD-CPI) K-means algorithm for clustering is possible to use. As a result, it detects the text that with improved accuracy. Ultimately, it reduces the processing time. The experimental result reveals that using WEKA-3.8 with the proposed technique shows improvement over the existing algorithms in terms of precision and Recall which enhance the accuracy in text mining