CARPe Posterum: A Convolutional Approach for Real-Time Pedestrian Path Prediction

Abstract

Pedestrian path prediction is an essential topic in computer vision and video understanding. Having insight into the movement of pedestrians is crucial for ensuring safe operation in a variety of applications including autonomous vehicles, social robots, and environmental monitoring. Current works in this area utilize complex generative or recurrent methods to capture many possible futures. However, despite the inherent real-time nature of predicting future paths, little work has been done to explore accurate and computationally efficient approaches for this task. To this end, we propose a convolutional approach for real-time pedestrian path prediction, CARPe. It utilizes a variation of Graph Isomorphism Networks in combination with an agile convolutional neural network design to form a fast and accurate path prediction approach. Notable results in both inference speed and prediction accuracy are achieved, improving FPS considerably in comparison to current state-of-the-art methods while delivering competitive accuracy on well-known path prediction datasets.

Pishgu: Universal Path Prediction Architecture through Graph Isomorphism and Attentive Convolution

“…While the focus is on pedestrians, Trajec-tron++ also predicts the future paths of vehicles to better understand how pedestrians might react to them. CARPe Posterum [27] utilizes graph isomorphism networks and a lightweight Convolutional Neural Network (CNN) for path prediction, considerably reducing computation and model size, targeting real-time applications. SSAGCN [25] uses an attention graph convolutional network and defines a new formulation to consider both social interactions as well as environmental factors as they can change the path that pedestrians may choose.…”

“…The fully connected structure assures that all the possible interactions between subjects are considered, and the network can extract all the important information from other neighbors. Similar to [27,24], Pishgu utilizes the a modified version of aggregation function introduced by [40] and constructs f i (the aggregated feature for node i) as follows:…”

“…We observe a proliferation of algorithms [32,31,23,42,27] that try to optimize the path prediction for a single context and perspective. Most existing approaches focus on an isolated domain and fail to evaluate the generality of their solution over different contexts and domains [4,25,31].…”

“…When it comes to real-world deployment and applications, a general domainagnostic approach that can accurately predict both pedestrians and vehicles across different views and perspectives is highly desirable. At the same time, path prediction is inherently a realtime task with a demand for one single accurate prediction for all subjects of interest at any point of time [27,19]. However, many existing path predictions rely on a spectrum of predictions with significantly large model sizes.…”

“…This paper introduces Pishgu 1 , a domain-agnostic path prediction approach for a wide range of applications. Similar to [27,24], Pishgu borrows Graph Isomorphism Network (GIN) [40] formulation for capturing the relative information between subjects. In addition to GIN, Pishgu goes further by leveraging attention mechanisms to create robustness against noisy data, a large number of parallel path predictions, and environmental alterations.…”