Attention Regulation for Efficient Semantic Segmentation on Unstructured Terrain

by Conference PaperPosted on No Comments

Abstract We present AR-Net, an efficient semantic segmentation pipeline for unstructured terrains. For applications such as autonomous navigation, it is essential to accurately and efficiently understand the unstructured scenes in outdoor and urban environments. Given RGB images as inputs, the AR-Net uses an encoder backbone to extract multi-scale features and a novel Attention-Regulation layer as …

Read more “Attention Regulation for Efficient Semantic Segmentation on Unstructured Terrain”

MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection

by Conference PaperPosted on No Comments

Abstract This paper proposes MambaST, a plug-and-play cross-spectral spatial-temporal fusion pipeline for efficient pedestrian detection. Several challenges exist for pedestrian detection in autonomous driving applications. First, it is difficult to perform accurate detection using RGB cameras under dark or low-light conditions. Cross-spectral systems must be developed to integrate complementary information from multiple sensor modalities, such …

Read more “MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection”

Bi-Capacity Choquet Integral for Sensor Fusion with Label Uncertainty

by Conference PaperPosted on No Comments

Abstract Sensor fusion combines data from multiple sensor sources to improve reliability, robustness, and accuracy of data interpretation. The Fuzzy Integral (FI), in particular, the Choquet integral (ChI), is often used as a powerful nonlinear aggregator for fusion across multiple sensors. However, existing supervised ChI learning algorithms typically require precise training labels for each input …

Read more “Bi-Capacity Choquet Integral for Sensor Fusion with Label Uncertainty”

BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection

by Conference PaperPosted on No Comments

Abstract We present BiPOCO, a Bi-directional trajectory predictor with POse COnstraints, for detecting anomalous activities of pedestrians in videos. In contrast to prior work based on feature reconstruction, our work identifies pedestrian anomalous events by forecasting their future trajectories and comparing the predictions with their expectations. We introduce a set of novel compositional pose-based losses …

Read more “BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection”

Leveraging Trajectory Prediction for Pedestrian Video Anomaly Detection

by Conference PaperPosted on No Comments

Abstract Video anomaly detection is a core problem in vision. Correctly detecting and identifying anomalous behaviors in pedestrians from video data will enable safety-critical applications such as surveillance, activity monitoring, and human-robot interaction. In this paper, we propose to leverage trajectory localization and prediction for unsupervised pedestrian anomaly event detection. Different than previous reconstruction-based approaches, …

Read more “Leveraging Trajectory Prediction for Pedestrian Video Anomaly Detection”

Angle-Regulated Transformer Network for Pedestrian Trajectory Prediction

by Conference PaperPosted on No Comments

Abstract Pedestrian trajectory prediction is an important topic in autonomous vehicle (AV) research. Accurate predictions of future pedestrian locations and movements are essential for AVs to safely and efficiently navigate in dense urban environments. The recently developed Transformer (TF) network has shown superior results for applications such as natural language processing and machine translation, but …

Read more “Angle-Regulated Transformer Network for Pedestrian Trajectory Prediction”

Multiple Instance Choquet Integral with Binary Fuzzy Measures for Remote Sensing Classifier Fusion with Imprecise Labels

by Conference PaperPosted on No Comments

Abstract Classifier fusion methods integrate complementary information from multiple classifiers or detectors and can aid remote sensing applications such as target detection and hyperspectral image analysis. The Choquet integral (CI), parameterized by fuzzy measures (FMs), has been widely used in the literature as an effective non-linear fusion framework. Standard supervised CI fusion algorithms often require …

Read more “Multiple Instance Choquet Integral with Binary Fuzzy Measures for Remote Sensing Classifier Fusion with Imprecise Labels”

Stochastic Sampling Simulation for Pedestrian Trajectory Prediction

by Conference PaperPosted on No Comments

Abstract Urban environments pose a significant challenge for autonomous vehicles (AVs) as they must safely navigate while in close proximity to many pedestrians. It is crucial for the AV to correctly understand and predict the future trajectories of pedestrians to avoid collision and plan a safe path. Deep neural networks (DNNs) have shown promising results …

Read more “Stochastic Sampling Simulation for Pedestrian Trajectory Prediction”

Efficient Binary Fuzzy Measure Representation and Choquet Integral Learning

by Conference PaperPosted on No Comments

Abstract The Choquet integral (ChI), a parametric function for information aggregation, is parameterized by the fuzzy measure (FM), which has 2^N real-valued variables for N inputs. However, the ChI incurs huge storage and computational burden due to its exponential complexity relative to N and, as a result, its calculation, storage, and learning becomes intractable for …

Read more “Efficient Binary Fuzzy Measure Representation and Choquet Integral Learning”