Most current algorithms for automatic glaucoma assessment using fundus images rely on handcrafted features based on segmentation, which are affected by the performance of the chosen segmentation method and the extracted features. Among other characteristics, convolutional neural networks (CNNs) are known because of their ability to learn highly discriminative features from raw pixel intensities. In this paper, we employed five different ImageNet-trained models (VGG16, VGG19, InceptionV3, ResNet50 and Xception) for automatic glaucoma assessment using fundus images. Results from an extensive validation using cross-validation and cross-testing strategies were compared with previous works in the literature. Using five public databases (1707 images), an average AUC of 0.9605 with a 95% confidence interval of 95.92–97.07%, an average specificity of 0.8580 and an average sensitivity of 0.9346 were obtained after using the Xception architecture, significantly improving the performance of other state-of-the-art works. Moreover, a new clinical database, ACRIMA, has been made publicly available, containing 705 labelled images. It is composed of 396 glaucomatous images and 309 normal images, which means, the largest public database for glaucoma diagnosis. The high specificity and sensitivity obtained from the proposed approach are supported by an extensive validation using not only the cross-validation strategy but also the cross-testing validation on, to the best of the authors’ knowledge, all publicly available glaucoma-labelled databases. These results suggest that using ImageNet-trained models is a robust alternative for automatic glaucoma screening system. All images, CNN weights and software used to fine-tune and test the five CNNs are publicly available, which could be used as a testbed for further comparisons.

This paper presents a video-based approach to detect the presence of parked vehicles in street lanes. Potential applications include the detection of illegally and double-parked vehicles in urban scenarios and incident detection on roads. The technique extracts information from low-level feature points (Harris corners) to create spatiotemporal maps that describe what is happening in the scene. The method neither relies on background subtraction nor performs any form of object tracking. The system has been evaluated using private and public data sets and has proven to be robust against common difficulties found in closed-circuit television video, such as varying illumination, camera vibration, the presence of momentary occlusion by other vehicles, and high noise levels.

The crouching or prone-on-the-ground observation heights suggested by the My Jump app are not practical in some settings, so users usually hold smartphones in a standing posture. This study aimed to analyze the reliability of My Jump 2 from the standardized and standing positions. Two identical smartphones recorded 195 countermovement jump executions from 39 active adult athletes at heights 30 and 90 cm, which were randomly assessed by three experienced observers. The between-observer reliability was high for both observation heights separately (ICC~0.99; SEM~0.6 cm; CV~1.3%) with low systematic (0.1 cm) and random (±1.7 cm) errors. The within-observer reliability for the three observers comparing the standardized and standing positions was high (ICC~0.99; SEM~0.7 cm; CV~1.4%), showing errors of 0.3 ± 1.9 cm. Observer 2 was the least accurate out of the three, although reliability remained similar to the levels of agreement found in the literature. The reliability of the mean observations in each height also revealed high reliability (ICC = 0.993; SEM = 0.51 cm; CV = 1.05%, error 0.32 ± 1.4 cm). Therefore, the reliability in the standing position did not change with respect to the standardized position, so it can be regarded as an alternative method to using My Jump 2 with practical added benefits.

This paper presents an approach to estimate traffic queue lengths. It does not rely on any sort of object tracking or background subtraction. The method is based on the detection of low level-features (corners) which can be associated to the presence of vehicles. Then, features are classified as moving or static. An analysis of the locations of static corners allows to measure queue lengths in meters. Errors are smaller than vehicle lengths. The algorithm has been tested with around the clock recordings in different real scenarios.

The aim of this study was to evaluate if the inertial measurement unit (IMU) Vmaxpro is a valid device to estimate vertical jump height (VJH) when compared to a motion capture system (MoCAP). Thirteen highly trained female volleyball players participated in this study which consisted of three sessions. After a familiarization session, two sessions comprised a warm-up followed by ten countermovement jumps, resting two min between each attempt. Jump height was measured simultaneously by Vmaxpro using take-off velocity and MoCAP using center-of-mass vertical excursion. Results show significant differences in jump height between devices (10.52 cm; p < 0.001; ES = 0.9), a very strong Spearman’s correlation (r_s = 0.84: p < 0.001), and a weak concordance correlation coefficient (CCC = 0.22; ρ = 0.861; C_b = 0.26). Regression analysis reveals very high correlations, high systematic error (8.46 cm), and a nonproportional random error (SEE = 1.67 cm). Bland–Altman plots show systematic error (10.6 cm) with 97.3 % of the data being within the LoA. In conclusion, Vmaxpro can be considered a valid device for the estimation of VJH, being a cheaper, portable, and manageable alternative to MoCAP. However, the magnitude of systematic error discourages its use where indistinguishable data from Vmaxpro and MoCAP are used unless the corresponding specific fitting equation is applied.

Velocity-based training is a contemporary method used by sports coaches to prescribe the optimal loading based on the velocity of movement of a load lifted. The most employed and accurate instruments to monitor velocity are linear position transducers. Alternatively, smartphone apps compute mean velocity after each execution by manual on-screen digitizing, introducing human error. In this paper, a video-based instrument delivering unattended, real-time measures of barbell velocity with a smartphone high-speed camera has been developed. A custom image-processing algorithm allows for the detection of reference points of a multipower machine to autocalibrate and automatically track barbell markers to give real-time kinematic-derived parameters. Validity and reliability were studied by comparing the simultaneous measurement of 160 repetitions of back squat lifts executed by 20 athletes with the proposed instrument and a validated linear position transducer, used as a criterion. The video system produced practically identical range, velocity, force, and power outcomes to the criterion with low and proportional systematic bias and random errors. Our results suggest that the developed video system is a valid, reliable, and trustworthy instrument for measuring velocity and derived variables accurately with practical implications for use by coaches and practitioners.