Siamese Network Object Tracking Algorithm Combining Attention Mechanism and Correlation Filter Theory

Aiming to solve the problem of tracking drift during movement, which was caused by the lack of discriminability of the feature information and the failure of a fixed template to adapt to the change of object appearance, the paper proposes an object tracking algorithm combining attention mechanism and correlation filter theory based on the framework of full convolutional Siamese neural networks. Firstly, the apparent information is processed by using the attention mechanism thought, where the object and search area features are optimized according to the spatial attention and channel attention module. At the same time, the cross-attention module is introduced to process the template branch and search area branch, respectively, which makes full use of the diversified context information of the search area. Then, the background perception correlation filter model with scale adaptation and learning rate adjustment is adopted into the model construction, using as a layer in the network model to realize the object template update. Finally, the optimal object location is determined according to the confidence map with similarity calculation. Experimental results show that the designed method in the paper can promote the object tracking performance under various challenging environments effectively; the success rate increases by 16.2%, and the accuracy rate increases by 16%.

The Source–Filter Theory of Speech

In the source-filter theory, the mechanism of speech production is described as a two-stage process: (a) The air flow coming from the lungs induces tissue vibrations of the vocal folds (i.e., two small muscular folds located in the larynx) and generates the “source” sound. Turbulent airflows are also created at the glottis or at the vocal tract to generate noisy sound sources. (b) Spectral structures of these source sounds are shaped by the vocal tract “filter.” Through the filtering process, frequency components corresponding to the vocal tract resonances are amplified, while the other frequency components are diminished. The source sound mainly characterizes the vocal pitch (i.e., fundamental frequency), while the filter forms the timbre. The source-filter theory provides a very accurate description of normal speech production and has been applied successfully to speech analysis, synthesis, and processing. Separate control of the source (phonation) and the filter (articulation) is advantageous for acoustic communications, especially for human language, which requires expression of various phonemes realized by a flexible maneuver of the vocal tract configuration. Based on this idea, the articulatory phonetics focuses on the positions of the vocal organs to describe the produced speech sounds. The source-filter theory elucidates the mechanism of “resonance tuning,” that is, a specialized way of singing. To increase efficiency of the vocalization, soprano singers adjust the vocal tract filter to tune one of the resonances to the vocal pitch. Consequently, the main source sound is strongly amplified to produce a loud voice, which is well perceived in a large concert hall over the orchestra. It should be noted that the source–filter theory is based upon the assumption that the source and the filter are independent from each other. Under certain conditions, the source and the filter interact with each other. The source sound is influenced by the vocal tract geometry and by the acoustic feedback from the vocal tract. Such source–filter interaction induces various voice instabilities, for example, sudden pitch jump, subharmonics, resonance, quenching, and chaos.

An observation algorithm for key motion states of skid-steered wheeled unmanned vehicle

With the increasing demand of military and civilian in the intelligent vehicles, the skid-steering theory has been widely used in unmanned ground vehicles, especially in unmanned military vehicles and unmanned surveillance platforms. Due to its driving environment complex and variable, which requires stricter dynamic control system. In order to improve the active safety performance of the skid-steering unmanned vehicle and develop the key technologies such as behavior decision planning technology, path tracking, and dynamic control technology, it is necessary to develop the dynamic state parameter observation system based on skid-steering theory. In this paper, an observation using Strong Track External Kalman Filter theory with noise matrix adaptive is designed to estimate vehicle kinematic parameters based on a 6 × 6 skid-steered unmanned vehicle. First, kinematic and dynamic model is built to analyze the characters of a skid-steered wheeled vehicle. Then a tire force estimation method based on dynamic model is presented to observe the tire longitude and vertical force. The tire force data is also used by Dugoff nonlinear model. Then an External Kalman Filter theory is designed to estimate vehicle kinematic parameters. To increase the accuracy and the robustness of the observer, the Strong Tracking EKF (STEKF) and noise adaptive adjustment is designed. Finally, a combined simulation using TruckSim and Simulink and the experiment using a 6 × 6 skid-steered unmanned vehicle verifies the efficiency of the observer. Results show that the observer is able to estimate the skid-steered wheeled vehicle states, and it also shows that the yaw rate result in the slip angle difference between each tire.

Realization of Cultural Filter in The Indonesian – English Translation of “Gundala Movie” Subtitle

Translating a movie subtitle from Indonesian into English should be done carefully because Indonesian and English have some differences which may lead to ineffective communication, such as the changing of structures, the difference of meanings, and also dissimilarity of corresponding cultures. This phenomenon might be a concern since many Indonesian movies have entered international audiences and won some international awards, such as the Gundala movie that is directed by Joko Anwar. This study focused on analyzing the cultural filter implemented in Indonesian – English audio-visual translation of Gundala movie subtitles. The analysis utilizes the cultural filter theory proposed by House (2015). The data analysis focused in this study includes the characters’ utterances in Indonesian and its English subtitle provided in the Gundala movie. The subject is the Indonesian transcription from verbal dialogues produced by the movie characters in Gundala movie and its English subtitles shown on the screen. The object of the study is words, phrases, and sentences produced by the characters in the Gundala movie. Most translations applied cultural filter achieves functional equivalence. Theoretically, the cultural filter can help the translator to achieve functional equivalence. Practically, for the next translation project, it could be a good challenge for the next researcher to explore the translation studies using this theory. Pedagogically, the reader should be more familiar with the cultural differences between Indonesian and English.

Filters in Strong BI-Algebras and Residuated Pseudo-SBI-Algebras

The concept of basic implication algebra (BI-algebra) has been proposed to describe general non-classical implicative logics (such as associative or non-associative fuzzy logic, commutative or non-commutative fuzzy logic, quantum logic). However, this algebra structure does not have enough characteristics to describe residual implications in depth, so we propose a new concept of strong BI-algebra, which is exactly the algebraic abstraction of fuzzy implication with pseudo-exchange principle (PEP). Furthermore, in order to describe the characteristics of the algebraic structure corresponding to the non-commutative fuzzy logics, we extend strong BI-algebra to the non-commutative case, and propose the concept of pseudo-strong BI (SBI)-algebra, which is the common extension of quantum B-algebras, pseudo-BCK/BCI-algebras and other algebraic structures. We establish the filter theory and quotient structure of pseudo-SBI- algebras. Moreover, based on prequantales, semi-uninorms, t-norms and their residual implications, we introduce the concept of residual pseudo-SBI-algebra, which is a common extension of (non-commutative) residual lattices, non-associative residual lattices, and also a special kind of residual partially-ordered groupoids. Finally, we investigate the filters and quotient algebraic structures of residuated pseudo-SBI-algebras, and obtain a unity frame of filter theory for various algebraic systems.