RECORD
ReMotENet: Efficient Relevant Motion Event Detection for Large-scale Home Surveillance Videos
Computer Vision and Pattern Recognition · Submitted 6 Jan 2018
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experiments demonstrate that our method can achieve comparable or event better performance than the object detection based method but with three to four orders of magnitude speedup (up to 20k times) on GPU devices.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. The traditional method usually consists of two separate steps, i.e., detecting moving objects with background subtraction running on the camera, and filtering out nuisance motion events (e.g., trees, cloud, shadow, rain/snow, flag) with deep learning based object detection and tracking running on cloud. The method is extremely slow and therefore not cost effective, and does not fully leverage the spatial-temporal redundancies with a pre-trained off-the-shelf object detector. To dramatically speedup relevant motion event detection and improve its performance, we propose a novel network for relevant motion event detection, ReMotENet, which is a unified, end-to-end data-driven method using spatial-temporal attention-based 3D ConvNets to jointly model the appearance and motion of objects-of-interest in a video. ReMotENet parses an entire video clip in one forward pass of a neural network to achieve significant speedup. Meanwhile, it exploits the properties of home surveillance videos, e.g., relevant motion is sparse both spatially and temporally, and enhances 3D ConvNets with a spatial-temporal attention model and reference-frame subtraction to encourage the network to focus on the relevant moving objects. Experiments demonstrate that our method can achieve comparable or event better performance than the object detection based method but with three to four orders of magnitude speedup (up to 20k times) on GPU devices. Our network is efficient, compact and light-weight. It can detect relevant motion on a 15s surveillance video clip within 4-8 milliseconds on a GPU and a fraction of second (0.17-0.39) on a CPU with a model size of less than 1MB.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. | background 1.00 | 0.19 | 0.03 | asserted 0.90 |
| s1 | The traditional method usually consists of two separate steps, i.e., detecting moving objects with background subtraction running on the camera, and filtering out nuisance motion events (e.g., trees, cloud, shadow, rain/snow, flag) with deep learning based object detection and tracking running on cloud. | background 0.99 | 0.05 | 0.02 | asserted 0.98 |
| s2 | The method is extremely slow and therefore not cost effective, and does not fully leverage the spatial-temporal redundancies with a pre-trained off-the-shelf object detector. | background 0.48 | 0.09 | 0.03 | asserted 1.00 |
| s3 | To dramatically speedup relevant motion event detection and improve its performance, we propose a novel network for relevant motion event detection, ReMotENet, which is a unified, end-to-end data-driven method using spatial-temporal attention-based 3D ConvNets to jointly model the appearance and motion of objects-of-interest in a video. | contribution 0.89 | 0.88 | 0.17 | asserted 0.99 |
| s4 | ReMotENet parses an entire video clip in one forward pass of a neural network to achieve significant speedup. | method 0.88 | 0.86 | 0.11 | asserted 1.00 |
| s5 | Meanwhile, it exploits the properties of home surveillance videos, e.g., relevant motion is sparse both spatially and temporally, and enhances 3D ConvNets with a spatial-temporal attention model and reference-frame subtraction to encourage the network to focus on the relevant moving objects. | method 0.94 | 0.83 | 0.05 | asserted 1.00 |
| s6 | Experiments demonstrate that our method can achieve comparable or event better performance than the object detection based method but with three to four orders of magnitude speedup (up to 20k times) on GPU devices. | result 1.00 | 0.96 | 0.53 | asserted 1.00 |
| s7 | Our network is efficient, compact and light-weight. | result 0.63 | 0.72 | 0.12 | asserted 1.00 |
| s8 | It can detect relevant motion on a 15s surveillance video clip within 4-8 milliseconds on a GPU and a fraction of second (0.17-0.39) on a CPU with a model size of less than 1MB. | result 1.00 | 0.95 | 0.16 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. The traditional method usually consists of two separate steps, i.e., detecting moving objects with background subtraction running on the camera, and filtering out nuisance motion events (e.g., trees, cloud, shadow, rain/snow, flag) with deep learning based object detection and tracking running on cloud. The method is extremely slow and therefore not cost effective, and does not fully leverage the spatial-temporal redundancies with a pre-trained off-the-shelf object detector. To dramatically speedup relevant motion event detection and improve its performance, we propose a novel network for relevant motion event detection, ReMotENet, which is a unified, end-to-end data-driven method using spatial-temporal attention-based 3D ConvNets to jointly model the appearance and motion of objects-of-interest in a video. ReMotENet parses an entire video clip in one forward pass of a neural network to achieve significant speedup. Meanwhile, it exploits the properties of home surveillance videos, e.g., relevant motion is sparse both spatially and temporally, and enhances 3D ConvNets with a spatial-temporal attention model and reference-frame subtraction to encourage the network to focus on the relevant moving objects. Experiments demonstrate that our method can achieve comparable or event better performance than the object detection based method but with three to four orders of magnitude speedup (up to 20k times) on GPU devices. Our network is efficient, compact and light-weight. It can detect relevant motion on a 15s surveillance video clip within 4-8 milliseconds on a GPU and a fraction of second (0.17-0.39) on a CPU with a model size of less than 1MB.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.