Object Permanence in Object Detection Leveraging Temporal Priors at
Inference Time
- URL: http://arxiv.org/abs/2211.15505v1
- Date: Mon, 28 Nov 2022 16:24:08 GMT
- Title: Object Permanence in Object Detection Leveraging Temporal Priors at
Inference Time
- Authors: Michael F\"urst, Priyash Bhugra, Ren\'e Schuster, Didier Stricker
- Abstract summary: We introduce explicit object permanence into two stage detection approaches drawing inspiration from particle filters.
Our detector uses the predictions of previous frames as additional proposals for the current one at inference time.
Experiments confirm the feedback loop improving detection performance by a up to 10.3 mAP with little computational overhead.
- Score: 11.255962936937744
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Object permanence is the concept that objects do not suddenly disappear in
the physical world. Humans understand this concept at young ages and know that
another person is still there, even though it is temporarily occluded. Neural
networks currently often struggle with this challenge. Thus, we introduce
explicit object permanence into two stage detection approaches drawing
inspiration from particle filters. At the core, our detector uses the
predictions of previous frames as additional proposals for the current one at
inference time. Experiments confirm the feedback loop improving detection
performance by a up to 10.3 mAP with little computational overhead.
Our approach is suited to extend two-stage detectors for stabilized and
reliable detections even under heavy occlusion. Additionally, the ability to
apply our method without retraining an existing model promises wide application
in real-world tasks.
Related papers
- DeTra: A Unified Model for Object Detection and Trajectory Forecasting [68.85128937305697]
Our approach formulates the union of the two tasks as a trajectory refinement problem.
To tackle this unified task, we design a refinement transformer that infers the presence, pose, and multi-modal future behaviors of objects.
In our experiments, we observe that ourmodel outperforms the state-of-the-art on Argoverse 2 Sensor and Open dataset.
arXiv Detail & Related papers (2024-06-06T18:12:04Z) - Detecting Every Object from Events [24.58024539462497]
We propose Detecting Every Object in Events (DEOE), an approach tailored for achieving high-speed, class-agnostic open-world object detection in event-based vision.
Our code is available at https://github.com/Hatins/DEOE.
arXiv Detail & Related papers (2024-04-08T08:20:53Z) - Learning Temporal Cues by Predicting Objects Move for Multi-camera 3D Object Detection [9.053936905556204]
We propose a model called DAP (Detection After Prediction), consisting of a two-branch network.
The features predicting the current objects from branch (i) is fused into branch (ii) to transfer predictive knowledge.
Our model can be used plug-and-play, showing consistent performance gain.
arXiv Detail & Related papers (2024-04-02T02:20:47Z) - Implicit Occupancy Flow Fields for Perception and Prediction in
Self-Driving [68.95178518732965]
A self-driving vehicle (SDV) must be able to perceive its surroundings and predict the future behavior of other traffic participants.
Existing works either perform object detection followed by trajectory of the detected objects, or predict dense occupancy and flow grids for the whole scene.
This motivates our unified approach to perception and future prediction that implicitly represents occupancy and flow over time with a single neural network.
arXiv Detail & Related papers (2023-08-02T23:39:24Z) - DetZero: Rethinking Offboard 3D Object Detection with Long-term
Sequential Point Clouds [55.755450273390004]
Existing offboard 3D detectors always follow a modular pipeline design to take advantage of unlimited sequential point clouds.
We have found that the full potential of offboard 3D detectors is not explored mainly due to two reasons: (1) the onboard multi-object tracker cannot generate sufficient complete object trajectories, and (2) the motion state of objects poses an inevitable challenge for the object-centric refining stage.
To tackle these problems, we propose a novel paradigm of offboard 3D object detection, named DetZero.
arXiv Detail & Related papers (2023-06-09T16:42:00Z) - Seeing BDD100K in dark: Single-Stage Night-time Object Detection via
Continual Fourier Contrastive Learning [3.4012007729454816]
Night-time object detection has been studied only sparsely, that too, via non-uniform evaluation protocols among the limited available papers.
In this paper, we bridge these 3 gaps:.
Lack of an uniform evaluation protocol (using a single-stage detector, due to its efficacy, and efficiency);.
A choice of dataset for benchmarking night-time object detection, and.
A novel method to address the limitations of current alternatives.
arXiv Detail & Related papers (2021-12-06T09:28:45Z) - Learning to Track Object Position through Occlusion [32.458623495840904]
Occlusion is one of the most significant challenges encountered by object detectors and trackers.
We propose a tracking-by-detection approach that builds upon the success of region based video object detectors.
Our approach achieves superior results on a dataset of furniture assembly videos collected from the internet.
arXiv Detail & Related papers (2021-06-20T22:29:46Z) - Learning to Track with Object Permanence [61.36492084090744]
We introduce an end-to-end trainable approach for joint object detection and tracking.
Our model, trained jointly on synthetic and real data, outperforms the state of the art on KITTI, and MOT17 datasets.
arXiv Detail & Related papers (2021-03-26T04:43:04Z) - Detecting Invisible People [58.49425715635312]
We re-purpose tracking benchmarks and propose new metrics for the task of detecting invisible objects.
We demonstrate that current detection and tracking systems perform dramatically worse on this task.
Second, we build dynamic models that explicitly reason in 3D, making use of observations produced by state-of-the-art monocular depth estimation networks.
arXiv Detail & Related papers (2020-12-15T16:54:45Z) - Slender Object Detection: Diagnoses and Improvements [74.40792217534]
In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects.
For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
arXiv Detail & Related papers (2020-11-17T09:39:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.