STI-GAN: Multimodal Pedestrian Trajectory Prediction Using Spatiotemporal Interactions and a Generative Adversarial Network
نویسندگان
چکیده
Predicting the future trajectories of multiple pedestrians in certain scenes has become a key task for ensuring that autonomous vehicles, socially interactive robots and other mobile platforms can navigate safely. The social interactions between people multimodal nature pedestrian movement make trajectory prediction challenging task. In this paper, problem is solved using generative adversarial network (GAN) graph attention (GAT) based on spatiotemporal interaction information about pedestrians. Our method, STI-GAN, an end-to-end GAN model simulates distribution to capture uncertainty predicted paths generate more reasonable trajectories. complex are modeled by GAT, used improve performance prediction. We verify robustness improvement our framework evaluating its results various datasets comparing them with several existing baselines. Compared methods, method reduces average displacement error (ADE) final (FDE) 21.9% 23.8% respectively.
منابع مشابه
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
In this work, we present the Text Conditioned Auxiliary Classifier Generative Adversarial Network, (TAC-GAN) a text to image Generative Adversarial Network (GAN) for synthesizing images from their text descriptions. Former approaches have tried to condition the generative process on the textual data; but allying it to the usage of class information, known to diversify the generated samples and ...
متن کاملDihedral angle prediction using generative adversarial networks
Several dihedral angles prediction methods were developed for protein structure prediction and their other applications. However, distribution of predicted angles would not be similar to that of real angles. To address this we employed generative adversarial networks (GAN) which showed promising results in image generation tasks. Generative adversarial networks are composed of two adversarially...
متن کاملGenerative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial perturbation that can easily fool the classifier network by using a gradient of each image. Simultaneously, the classifier network is trained to classify correctly bo...
متن کاملIVE-GAN: Invariant Encoding Generative Adversarial Networks
Generative adversarial networks (GANs) are a powerful framework for generative tasks. However, they are difficult to train and tend to miss modes of the true data generation process. Although GANs can learn a rich representation of the covered modes of the data in their latent space, the framework misses an inverse mapping from data to this latent space. We propose Invariant Encoding Generative...
متن کاملDefense-gan: Protecting Classifiers against Adversarial Attacks Using Generative Models
In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can cause misclassification of legitimate images. We propose Defense-GAN, a new framework leveraging the expressive capability of generative models to defend de...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2021
ISSN: ['2169-3536']
DOI: https://doi.org/10.1109/access.2021.3069134