SiamFDA: feature dynamic activation siamese network for visual tracking.

In this paper, we present a novel anchor-free visual tracking framework, referred to as feature dynamic activation siamese network (SiamFDA), which addresses the issue of ignoring global spatial information in current Siamese network-based tracking algorithms. Our approach captures long-range dependencies between distant pixels in space, which enables robustness to unreliable regions. Additionally, we introduce a hierarchical feature selector that adaptively activates features at different layers, and an adaptive sample label assignment method to further improve tracking performance. Our extensive evaluations on six benchmark datasets, including VOT-2018, VOT-2019, GOT10k, LaSOT, OTB-2015, and OTB-2013, demonstrate that SiamFDA outperforms several state-of-the-art trackers in various challenging scenarios, with a real-time frame rate of 40 frames per second.

Motion sensitive network for action recognition in control and decision-making of autonomous systems.

Spatial-temporal modeling is crucial for action recognition in videos within the field of artificial intelligence. However, robustly extracting motion information remains a primary challenge due to temporal deformations of appearances and variations in motion frequencies between different actions. In order to address these issues, we propose an innovative and effective method called the Motion Sensitive Network (MSN), incorporating the theories of artificial neural networks and key concepts of autonomous system control and decision-making. Specifically, we employ an approach known as Spatial-Temporal Pyramid Motion Extraction (STP-ME) module, adjusting convolution kernel sizes and time intervals synchronously to gather motion information at different temporal scales, aligning with the learning and prediction characteristics of artificial neural networks. Additionally, we introduce a new module called Variable Scale Motion Excitation (DS-ME), utilizing a differential model to capture motion information in resonance with the flexibility of autonomous system control. Particularly, we employ a multi-scale deformable convolutional network to alter the motion scale of the target object before computing temporal differences across consecutive frames, providing theoretical support for the flexibility of autonomous systems. Temporal modeling is a crucial step in understanding environmental changes and actions within autonomous systems, and MSN, by integrating the advantages of Artificial Neural Networks (ANN) in this task, provides an effective framework for the future utilization of artificial neural networks in autonomous systems. We evaluate our proposed method on three challenging action recognition datasets (Kinetics-400, Something-Something V1, and Something-Something V2). The results indicate an improvement in accuracy ranging from 1.1% to 2.2% on the test set. When compared with state-of-the-art (SOTA) methods, the proposed approach achieves a maximum performance of 89.90%. In ablation experiments, the performance gain of this module also shows an increase ranging from 2% to 5.3%. The introduced Motion Sensitive Network (MSN) demonstrates significant potential in various challenging scenarios, providing an initial exploration into integrating artificial neural networks into the domain of autonomous systems.

Superoxide radical mediated Mn(III) formation is the key process in the activation of peroxymonosulfate (PMS) by Mn-incorporated bacterial-derived biochar.

Biochar was used as a heterogeneous activator for peroxymonosulfate (PMS), and the activation performance strongly depended on the structure, functional groups, and modification of the biochar. In this study, a new type of modified biochar was synthesized by utilizing the Mn(II) adsorption capacity of bacteria. After one-step pyrolysis of Mn(II)-adsorbed bacterial cells at 800 °C, a Mn-incorporated bacterial-derived biochar (Mn-BBC) was successfully produced. It exhibited structural heterogeneity, with MnO located at the surface of the BBC matrix, as shown on the result of SEM and XRD. Compared to BBC, Mn-BBC showed a 10-fold increase (0.0727 min-1 versus 0.0069 min-1) of pollutant removal rate. In addition, it also showed anti-interference capacity against common water matrix (except 10 mM CO32-) and great stability/reusability. Chemical quenching, electron spin resonance, and pyrophosphate trapping indicated an indirect but important role of the superoxide, formed during the self-decomposition of PMS. The MnO on Mn-BBC can be oxidized by superoxide to produce surface Mn(III), which then binds to PMS and forms a surface complex. This complex promotes electron transfer from the pollutant to the Mn-BBC, facilitating the oxidation of the contaminants. Overall, this study confirmed the PMS activation capacity and mechanism of Mn-BBC, which expands the application of BBC-based materials derived from metal-adsorbed microbes.

Pilot study of feature-based algorithm for breech face comparison.

A novel feature-based method, which is scale invariant feature transform (SIFT) and RANdom SAmple Consensus (RANSAC) integration algorithm, is introduced to promote the automated identification of the breech face impression, the most common mark left on the cartridge used for firearm evidence. SIFT algorithm is employed to extract the local extrema from examined impression as keypoints representing its invariant features, and to build the feature descriptor for each keypoint based on its local gradients in neighborhood. RANSAC is used to improve the matching performance among these keypoints and feature descriptors. With hypothesize-and-verify methods, RANSAC is able to construct the best model fitting initial matching pairs of keypoints and to guarantee the robust comparison result. Validation tests using 40 cartridge cases fired from pistols with 10 consecutively manufactured slides yielded a clear separation result, which strongly supports the effectiveness of the ensemble algorithm of SIFT and RANSAC. This application indicates the practical feasibility of feature-based algorithm and image processing technique in forensic science.

Intra-session test-retest reliability of magnitude and structure of center of pressure from the Nintendo Wii Balance Board™ for a visually impaired and normally sighted population.

Individuals with visual impairment (VI) have irreparable damage to one of the input streams contributing to postural stability. Here, we evaluated the intra-session test-retest reliability of the Wii Balance Board (WBB) for measuring Center of Pressure (COP) magnitude and structure, i.e. approximate entropy (ApEn) in fourteen legally blind participants and 21 participants with corrected-to-normal vision. Participants completed a validated balance protocol which included four sensory conditions: double-leg standing on a firm surface with eyes open (EO-firm); a firm surface with eyes closed (EC-firm); a foam surface with EO (EO-foam); and a foam surface with EC (EC-foam). Participants performed the full balance protocol twice during the session, separated by a period of 15min, to determine the intraclass correlation coefficient (ICC). Absolute reliability was determined by the standard error of measurement (SEM). The minimal difference (MD) was estimated to determine clinical significance for future studies. COP measures were derived from data sent by the WBB to a laptop via Bluetooth. COP scores increased with the difficulty of sensory condition indicating WBB sensitivity (all p<0.01). ICCs in the VI group ranged from 0.73 to 0.95, indicating high to very high correlations, and the normal group showed moderate to very high ICCs (0.62-0.94). The SEM was comparable between groups regardless of between-subject variability. The reliability of the WBB makes it practical to screen for balance impairment among VI persons.