Ensemble Video Object Cut in Highly Dynamic Scenes

By Xiaobo Ren, Tony X. Han, Zhihai He. 2013

39 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Recognition in Terra Incognita (2018, methodology): “[16] demonstrates a graph-cut method that uses background modeling and foreground object saliency to segment foreground in camera trap sequences.”
Animal Detection From Highly Cluttered Natural Scenes Using Spatiotemporal Object Region Proposals and Patch Verification (2016, unknown): “methods: (1) EC, Ensemble graph Cuts developed in our previous work [34]; (2) YOLO, a fast unified object detection algorithm which detect objects in single inference [45]; (3) Fast-RCNN [10]; (4) Faster-RCNN [11], an improved version of Fast-RCNN which propose candidates using fully convolutional n”
Camera-trap images segmentation using multi-layer robust principal component analysis (2017, methodology): “developed a method to segment images from dynamic scenes, including camera-trap images; the method uses Bag of Words (BoW), Histogram of Oriented Gradients (HOG), and graph cut energy minimization [7].”
Efficient Pipeline for Camera Trap Image Review (2019, methodology): “The computer vision community has been making strides towards automating the species classification challenge in camera traps [1, 2, 4–16], but it has proven difficult to to apply models trained in one region to images collected in different geographic areas.”
A computer vision for animal ecology. (2018, background): “Stateoftheart approaches (Ren et al., 2013; Zhang et al., 2016) can both identify images of interest, as well as define where within an image an animal occurs.”
Optical Flow with Semantic Segmentation and Localized Layers (2016, background): “There is significant and increasing interest in the field [12, 14, 32, 41, 42, 57] but the definition of the problem varies between identifying coherent motions or coherent objects regions.”
Foreground object detection in highly dynamic scenes using saliency (2014, methodology): “Table 1 shows the accuracy of empty frame detection on the dataset in comparison with (1) RPCA+OF: the Robust PCA plus optical flow approach [14] and (2) EVOC: the video object graph cut approach [4].”
Towards automatic wild animal monitoring: Identification of animal species in camera-trap images using very deep convolutional neural networks (2016, methodology): “These images were generated using an automatic segmentation algorithm described in [15].”
The iWildCam 2019 Challenge Dataset (2019, background): “Automating camera trap labeling is not a new challenge for the computer vision community [1, 3–10, 12–17].”
Coupled ensemble graph cuts and object verification for animal segmentation from highly cluttered videos (2015, unknown): “We follow the idea developed in our previous work [9] to fuse background-foreground classification results of neighboring frames to further refine the segmentation in an iterative manner.”
Deep convolutional neural network based species recognition for wild animal monitoring (2014, methodology): “Index Terms— Species recognition, wild animal monitor, image classification, deep convolutional neural networks, large scale learning”