Probabilistic Future Prediction for Video Scene Understanding

2018

Predicting the future in real-world settings, particularly from raw sensory observations such as images, is exceptionally challenging. Real-world events can be stochastic and unpredictable, and the high dimensionality and complexity of natural images requires the predictive model to build an intricate understanding of the natural world. Many existing methods tackle this problem by making simplifying assumptions about the environment. One common assumption is that the outcome is deterministic and there is only one plausible future. This can lead to low-quality predictions in real-world settings with stochastic dynamics. In this paper, we develop a stochastic variational video prediction (SV2P) method that predicts a different possible future for each sample of its latent variables. To the best of our knowledge, our model is the first to provide effective stochastic multi-frame prediction for real-world video. We demonstrate the capability of the proposed method in predicting detailed...

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019

Anticipating actions before they are executed is crucial for a wide range of practical applications including autonomous driving and robotics. While most prior work in this area requires partial observation of executed actions, in the paper we focus on anticipating actions seconds before they start. Our proposed approach is the fusion of a purely anticipatory model with a complementary model constrained to reason about the present. In particular, the latter predicts present action and scene attributes, and reasons about how they evolve over time. By doing so, we aim at modeling action anticipation at a more conceptual level than directly predicting future actions. Our model outperforms previously reported methods on the EPIC-KITCHENS and Breakfast datasets.

Cornell University - arXiv, 2022

In self-driving, predicting future in terms of location and motion of all the agents around the vehicle is a crucial requirement for planning. Recently, a new joint formulation of perception and prediction has emerged by fusing rich sensory information perceived from multiple cameras into a compact bird's-eye view representation to perform prediction. However, the quality of future predictions degrades over time while extending to longer time horizons due to multiple plausible predictions. In this work, we address this inherent uncertainty in future predictions with a stochastic temporal model. Our model learns temporal dynamics in a latent space through stochastic residual updates at each time step. By sampling from a learned distribution at each time step, we obtain more diverse future predictions that are also more accurate compared to previous work, especially stretching both spatially further regions in the scene and temporally over longer time horizons. Despite separate processing of each time step, our model is still efficient through decoupling of the learning of dynamics and the generation of future predictions.

2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

In this paper we present a conceptually simple but surprisingly powerful method for visual prediction which combines the effectiveness of mid-level visual elements with temporal modeling. Our framework can be learned in a completely unsupervised manner from a large collection of videos. However, more importantly, because our approach models the prediction framework on these mid-level elements, we can not only predict the possible motion in the scene but also predict visual appearances-how are appearances going to change with time. This yields a visual "hallucination" of probable events on top of the scene. We show that our method is able to accurately predict and visualize simple future events; we also show that our approach is comparable to supervised methods for event prediction.

2019

Anticipating the future positions of the surrounding vehicles is a crucial task foran autonomous vehicle in order to drive safely. To foresee complex manoeuvresfor longer time horizons, a framework ...

arXiv (Cornell University), 2024

In this paper, we propose a novel video depth estimation approach, FutureDepth, which enables the model to implicitly leverage multi-frame and motion cues to improve depth estimation by making it learn to predict the future at training. More specifically, we propose a future prediction network, F-Net, which takes the features of multiple consecutive frames and is trained to predict multi-frame features one time step ahead iteratively. In this way, F-Net learns the underlying motion and correspondence information, and we incorporate its features into the depth decoding process. Additionally, to enrich the learning of multiframe correspondence cues, we further leverage a reconstruction network, R-Net, which is trained via adaptively masked auto-encoding of multiframe feature volumes. At inference time, both F-Net and R-Net are used to produce queries to work with the depth decoder, as well as a final refinement network. Through extensive experiments on several benchmarks, i.e., NYUDv2, KITTI, DDAD, and Sintel, which cover indoor, driving, and open-domain scenarios, we show that FutureDepth significantly improves upon baseline models, outperforms existing video depth estimation methods, and sets new state-of-the-art (SOTA) accuracy. Furthermore, FutureDepth is more efficient than existing SOTA video depth estimation models and has similar latencies when comparing to monocular models.

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

The design of a safe and reliable Autonomous Driving stack (ADS) is one of the most challenging tasks of our era. These ADS are expected to be driven in highly dynamic environments with full autonomy, and a reliability greater than human beings. In that sense, to efficiently and safely navigate through arbitrarily complex traffic scenarios, ADS must have the ability to forecast the future trajectories of surrounding actors. Current state-of-the-art models are typically based on Recurrent, Graph and Convolutional networks, achieving noticeable results in the context of vehicle prediction. In this paper we explore the influence of attention in generative models for motion prediction, considering both physical and social context to compute the most plausible trajectories. We first encode the past trajectories using a LSTM network, which serves as input to a Multi-Head Self-Attention module that computes the social context. On the other hand, we formulate a weighted interpolation to calculate the velocity and orientation in the last observation frame in order to calculate acceptable target points, extracted from the driveable of the HDMap information, which represents our physical context. Finally, the input of our generator is a white noise vector sampled from a multivariate normal distribution while the social and physical context are its conditions, in order to predict plausible trajectories. We validate our method using the Argoverse Motion Forecasting Benchmark 1.1, achieving competitive unimodal results. Our code is publicly available at https://github.com/Cram3r95/mapfe4mp .

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

Nowadays, our mobility systems are evolving into the era of intelligent vehicles that aim to improve road safety. Due to their vulnerability, pedestrians are the users who will benefit the most from these developments. However, predicting their trajectory is one of the most challenging concerns. Indeed, accurate prediction requires a good understanding of multiagent interactions that can be complex. Learning the underlying spatial and temporal patterns caused by these interactions is even more of a competitive and open problem that many researchers are tackling. In this paper, we introduce a model called PRediction Transformer (PReTR) that extracts features from the multi-agent scenes by employing a factorized spatiotemporal attention module. It shows less computational needs than previously studied models with empirically better results. Besides, previous works in motion prediction suffer from the exposure bias problem caused by generating future sequences conditioned on model prediction samples rather than groundtruth samples. In order to go beyond the proposed solutions, we leverage encoder-decoder Transformer networks for parallel decoding a set of learned object queries. This non-autoregressive solution avoids the need for iterative conditioning and arguably decreases training and testing computational time. We evaluate our model on the ETH/UCY datasets, a publicly available benchmark for pedestrian trajectory prediction. Finally, we justify our usage of the parallel decoding technique by showing that the trajectory prediction task can be better solved as a non-autoregressive task.

International Journal of Recent Contributions from Engineering, Science & IT (iJES)

Deep neural networks are becoming central in several areas of computer vision. While there have been a lot of studies regarding the classification of images and videos, future frame prediction is still a rarely investigated approach, and even some applications could make good use of the knowledge regarding the next frame of an image sequence in pixel-space. Examples include video compression and autonomous agents in robotics that have to act in natural environments. Learning how to forecast the future of an image sequence requires the system to understand and efficiently encode the content and dynamics for a certain period. It is viewed as a promising avenue from which even supervised tasks could benefit since labeled video data is limited and hard to obtain. Therefore, this work gives an overview of scientific advances covering future frame prediction and proposes a recurrent network model which utilizes recent techniques from deep learning research. The presented architecture is b...