Fusion Object Detection and Action Recognition to Predict Violent Action.

In the context of Shared Autonomous Vehicles, the need to monitor the environment inside the car will be crucial. This article focuses on the application of deep learning algorithms to present a fusion monitoring solution which was three different algorithms: a violent action detection system, which recognizes violent behaviors between passengers, a violent object detection system, and a lost items detection system. Public datasets were used for object detection algorithms (COCO and TAO) to train state-of-the-art algorithms such as YOLOv5. For violent action detection, the MoLa InCar dataset was used to train on state-of-the-art algorithms such as I3D, R(2+1)D, SlowFast, TSN, and TSM. Finally, an embedded automotive solution was used to demonstrate that both methods are running in real-time.

Sensor Fusion Approach for Multiple Human Motion Detection for Indoor Surveillance Use-Case.

Multi-human detection and tracking in indoor surveillance is a challenging task due to various factors such as occlusions, illumination changes, and complex human-human and human-object interactions. In this study, we address these challenges by exploring the benefits of a low-level sensor fusion approach that combines grayscale and neuromorphic vision sensor (NVS) data. We first generate a custom dataset using an NVS camera in an indoor environment. We then conduct a comprehensive study by experimenting with different image features and deep learning networks, followed by a multi-input fusion strategy to optimize our experiments with respect to overfitting. Our primary goal is to determine the best input feature types for multi-human motion detection using statistical analysis. We find that there is a significant difference between the input features of optimized backbones, with the best strategy depending on the amount of available data. Specifically, under a low-data regime, event-based frames seem to be the preferred input feature type, while higher data availability benefits the combined use of grayscale and optical flow features. Our results demonstrate the potential of sensor fusion and deep learning techniques for multi-human tracking in indoor surveillance, although it is acknowledged that further studies are needed to confirm our findings.

AI based monitoring violent action detection data for in-vehicle scenarios.

With the evolution of technology associated with mobility and autonomy, Shared Autonomous Vehicles will be a reality. To ensure passenger safety, there is a need to create a monitoring system inside the vehicle capable of recognizing human actions. We introduce two datasets to train human action recognition inside the vehicle, focusing on violence detection. The InCar dataset tackles violent actions for in-car background which give us more realistic data. The InVicon dataset although doesn't have the realistic background as the InCar dataset can provide skeleton (3D body joints) data. This datasets were recorded with RGB, Depth, Thermal, Event-based, and Skeleton data. The resulting dataset contains 6 400 video samples and more than 3 million frames, collected from sixteen distinct subjects. The dataset contains 58 action classes, including violent and neutral (i.e., non-violent) activities.

Large-scale neuroanatomy using LASSO: Loop-based Automated Serial Sectioning Operation.

Serial section transmission electron microscopy (ssTEM) is the most promising tool for investigating the three-dimensional anatomy of the brain with nanometer resolution. Yet as the field progresses to larger volumes of brain tissue, new methods for high-yield, low-cost, and high-throughput serial sectioning are required. Here, we introduce LASSO (Loop-based Automated Serial Sectioning Operation), in which serial sections are processed in "batches." Batches are quantized groups of individual sections that, in LASSO, are cut with a diamond knife, picked up from an attached waterboat, and placed onto microfabricated TEM substrates using rapid, accurate, and repeatable robotic tools. Additionally, we introduce mathematical models for ssTEM with respect to yield, throughput, and cost to access ssTEM scalability. To validate the method experimentally, we processed 729 serial sections of human brain tissue (~40 nm x 1 mm x 1 mm). Section yield was 727/729 (99.7%). Sections were placed accurately and repeatably (x-direction: -20 ± 110 µm (1 s.d.), y-direction: 60 ± 150 µm (1 s.d.)) with a mean cycle time of 43 s ± 12 s (1 s.d.). High-magnification (2.5 nm/px) TEM imaging was conducted to measure the image quality. We report no significant distortion, information loss, or substrate-derived artifacts in the TEM images. Quantitatively, the edge spread function across vesicle edges and image contrast were comparable, suggesting that LASSO does not negatively affect image quality. In total, LASSO compares favorably with traditional serial sectioning methods with respect to throughput, yield, and cost for large-scale experiments, and represents a flexible, scalable, and accessible technology platform to enable the next generation of neuroanatomical studies.

A Suite of Transgenic Driver and Reporter Mouse Lines with Enhanced Brain-Cell-Type Targeting and Functionality.

Modern genetic approaches are powerful in providing access to diverse cell types in the brain and facilitating the study of their function. Here, we report a large set of driver and reporter transgenic mouse lines, including 23 new driver lines targeting a variety of cortical and subcortical cell populations and 26 new reporter lines expressing an array of molecular tools. In particular, we describe the TIGRE2.0 transgenic platform and introduce Cre-dependent reporter lines that enable optical physiology, optogenetics, and sparse labeling of genetically defined cell populations. TIGRE2.0 reporters broke the barrier in transgene expression level of single-copy targeted-insertion transgenesis in a wide range of neuronal types, along with additional advantage of a simplified breeding strategy compared to our first-generation TIGRE lines. These novel transgenic lines greatly expand the repertoire of high-precision genetic tools available to effectively identify, monitor, and manipulate distinct cell types in the mouse brain.

Embedding of cortical representations by the superficial patch system.

Pyramidal cells in layers 2 and 3 of the neocortex of many species collectively form a clustered system of lateral axonal projections (the superficial patch system--Lund JS, Angelucci A, Bressloff PC. 2003. Anatomical substrates for functional columns in macaque monkey primary visual cortex. Cereb Cortex. 13:15-24. or daisy architecture--Douglas RJ, Martin KAC. 2004. Neuronal circuits of the neocortex. Annu Rev Neurosci. 27:419-451.), but the function performed by this general feature of the cortical architecture remains obscure. By comparing the spatial configuration of labeled patches with the configuration of responses to drifting grating stimuli, we found the spatial organizations both of the patch system and of the cortical response to be highly conserved between cat and monkey primary visual cortex. More importantly, the configuration of the superficial patch system is directly reflected in the arrangement of function across monkey primary visual cortex. Our results indicate a close relationship between the structure of the superficial patch system and cortical responses encoding a single value across the surface of visual cortex (self-consistent states). This relationship is consistent with the spontaneous emergence of orientation response-like activity patterns during ongoing cortical activity (Kenet T, Bibitchkov D, Tsodyks M, Grinvald A, Arieli A. 2003. Spontaneously emerging cortical representations of visual attributes. Nature. 425:954-956.). We conclude that the superficial patch system is the physical encoding of self-consistent cortical states, and that a set of concurrently labeled patches participate in a network of mutually consistent representations of cortical input.