Recently, the Kernelized Correlation Filters tracker (KCF) achieved competitive performance and robustness in visual object tracking. On the other hand, visual trackers are not typically used in multiple object tracking. In this paper, we investigate how a robust visual tracker like KCF can improve multiple object tracking. Since KCF is a fast tracker, many KCF can be used in parallel and still result in fast tracking. We built a multiple object tracking system based on KCF and background subtraction. Background subtraction is applied to extract moving objects and get their scale and size in combination with KCF outputs, while KCF is used for data association and to handle fragmentation and occlusion problems. As a result, KCF and background subtraction help each other to take tracking decision at every frame. Sometimes KCF outputs are the most trustworthy (e.g. during occlusion), while in some other cases, it is the background subtraction outputs. To validate the effectiveness of our system, the algorithm was tested on four urban traffic videos from a standard dataset. Results show that our method is competitive with state-of-the-art trackers even if we use a much simpler data association step.
We report a direct measurement of the imaginary part of the surface tension of water through a dynamic scheme using a thin vertical glass fiber of diameter of 3 𝜇m with one end glued onto a cantilever beam and the other end touching a water-air interface. The frequency dependence of the dissipation factor experienced by the glass fiber is exactly calculated through measuring the phase delay with various frequencies when the glass fiber is forced to oscillate vertically. We find the same intercept at the dissipation factor axis for different frequency dependences of the dissipation factor for different depths by which the glass fiber is dipped into water. This nonzero dissipation factor at zero frequency presents direct evidence of the existence of the imaginary part of surface tension of water and yields a complex surface tension of water 𝜎 * = 0.073 + 𝑖(0.017 ± 0.002) N/m at room temperature.
We discuss theoretically the effect of complex surface tension on the dispersion relation of a capillary wave, and we deduce an analytical expression for the attenuation of a capillary wave due to the imaginary part of the complex surface tension. We make use of our recently developed apparent energy dissipation spectroscopy to measure the attenuation of a propagating capillary wave at an air− water interface via a microrheometer based on an atomic force microscope. We show that the revised theoretical expression for the attenuation of a capillary wave can satisfactorily explain the abnormal attenuation of such a wave, which stems from both the apparent energy dissipation spectrum and optical scattering, and we obtain the same value for the imaginary part of the surface tension of water. ■ INTRODUCTIONThe term "capillary wave" usually refers to the mechanical wave at an air−liquid or a liquid−liquid interface 1−3 and is an important way to reveal the properties of the interface, such as the viscoelasticity of a Langmuir−Blodgett film 4,5 or another absorbed molecular layer. 6,7 The attenuation of a capillary wave is described by the expression 2,8where ν is the dynamic viscosity of the liquid and q is the surface wave vector. The attenuation of a capillary wave comes entirely from the viscosity of the fluid. The viscosity of the air− liquid interface is unclear. Goodrich 9 suggested that the anisotropic momentum transport, which is involved in the molecularly diffuse interfacial region, will lead to surface viscosity effects. Earnshaw 10 developed this theory and showed that the surface viscosity causes the imaginary part of surface tension, i.e., the energy dissipation. However, careful experiments by optical techniques show that the surface viscosity is zero or very small for the surfaces of many air−liquid interfaces. 11−13 We noticed that in physics, the surface viscosity and the imaginary part of the surface tension are two different concepts. Both of these concepts can cause damping of the capillary wave. The difference is that whereas the surface viscosity is related to the velocity, the surface tension is related to the displacement. In other words, the surface viscosity is frequency-dependent, and the surface tension is frequency-independent. To date, finding experimental evidence of the imaginary part of the surface tension is still an open problem.The atomic force microscope (AFM) was invented for detection on the submicrometer to subnanometer scale and is an appropriate instrument for probing capillary waves. Recently, a microrheometer developed by us, which is based on the atomic force microscope, has been proven to be an instrument useful for exploring air−liquid interfaces. 14 By using this microrheometer and its corresponding analysis method of apparent dissipation factor frequency spectroscopy (ADFFS), 15 we can obtain those vibrational modes of a complex system that are difficult to detect by means such as X-ray scattering 7 and optical techniques. 2 Compared to these techniques, the advantage...
Background At present, the residual film pollution in cotton fields is crucial. The commonly used recycling method is the manual-driven recycling machine, which is heavy and time-consuming. The development of a visual navigation system for the recovery of residual film is conducive, in order to improve the work efficiency. The key technology in the visual navigation system is the cotton stubble detection. A successful cotton stubble detection can ensure the stability and reliability of the visual navigation system. Methods Firstly, it extracts the three types of texture features of GLCM, GLRLM and LBP, from the three types of images of stubbles, residual films and broken leaves between rows. It then builds three classifiers: Random Forest, Back Propagation Neural Network and Support Vector Machine in order to classify the sample images. Finally, the possibility of improving the classification accuracy using the texture features extracted from the wavelet decomposition coefficients, is discussed. Results The experiment proves that the GLCM texture feature of the original image has the best performance under the Back Propagation Neural Network classifier. As for the different wavelet bases, the vertical coefficient texture feature of coif3 wavelet decomposition, combined with the texture feature of the original image, is the feature having the best classification effect. Compared with the original image texture features, the classification accuracy is increased by 3.8%, the sensitivity is increased by 4.8%, and the specificity is increased by 1.2%. Conclusions The algorithm can complete the task of stubble detection in different locations, different periods and abnormal driving conditions, which shows that the wavelet coefficient texture feature combined with the original image texture feature is a useful fusion feature for detecting stubble and can provide a reference for different crop stubble detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.