Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle

By Dariu M. Gavrila, Stefan Munder. International Journal of Computer Vision, 2007

609 citations recorded by the source corpus.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/91335d9335e4fd06de48d769d1b79eaded4e431b

How researchers see this paper

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

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes (2011, background): “Two main categories can be distinguished: those applied to intensity images and those working on range data or depth images.”
Model-free detection and tracking of dynamic objects with 2D lidar (2015, methodology): “To train the system for best performing parameter sets, we follow an approach similar to that described by Gavrila and Munder (2007) as follows: both precision P and recall R are functions of system parameters, thus if the number of system parameters exceeds one, the set of all feasible (R,P) pairs…”
A mobile vision system for robust multi-person tracking (2008, background): “In such cases, background subtraction is no longer a viable option, and tracking-bydetection approaches seem to be the most promising alternative [22] [10] [15] [28].”
Sparse-MLP: A Fully-MLP Architecture with Conditional Computation (2021, methodology): “2017) has been successfully applied to many domains and tasks (Gavrila and Munder 2006; Hu, Palreddy, and Tompkins 1997; Tani and Nolfi 1999; Sminchisescu et al. 2004; Zeevi, Meir, and Adler 1997).”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, methodology): “Similarly, Gavrila & Munder (2007) integrate the same cues into a detection and tracking system with a cascade of modules.”
New features and insights for pedestrian detection (2010, background): “Pedestrian detection has been a focus of recent research due to its importance for practical applications such as automotive safety [11, 8] and visual surveillance [23].”
3D Traffic Scene Understanding From Movable Platforms (2014, background): “For a long time, dynamic objects have been considered either in isolation [5], [26], [27], [52] or using simple motion [9], [23], [42], [47], [63] or social interaction [15], [62] models.”
Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010, methodology): “Gavrila et al. [55], [70] verify detections by performing cross correlation between the left image of a stereo pair and the isolated silhouette computed by the Chamfer system in the right image.”
Scaling Vision with Sparse Mixture of Experts (2021, background): “MoEs have successfully used this form of conditional computation in a range of applications [23, 30, 58, 55, 67].”
Monocular Pedestrian Detection: Survey and Experiments (2009, methodology): “…(HOG) features combined with a linear SVM [11]; IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 31, NO. 12, DECEMBER 2009 2179 . neural network using local receptive fields (NN/LRF) [75]; and . combined hierarchical shape matching and texturebased NN/LRF classification [23].”
Pedestrian Detection: An Evaluation of the State of the Art (2012, background): “For an overview of how detectors are incorporated into full automotive systems that utilize stereo, scene geometry, tracking, or other imaging modalities (e.g., [30], [38], [39], [40], [41]), we refer readers to [2], [42], [43].”
Human detection from images and videos: A survey (2016, methodology): “For instance, in [47, 110] shape-normalised textural regions were identified by using human shape templates to warp image areas.”
A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching (2007, methodology): “A comparison of state-of-the-art pedestrian systems [7], [11], [19], [21], using the same data set and performance metrics, is worthwhile for future work.”
Pedestrian Protection Systems: Issues, Survey, and Challenges (2007, methodology): “The DaimlerChrysler’s research system is described in [35], which builds on their earlier research in [34].”
Pedestrian detection: A benchmark (2009, background): “Automotive applications [12, 14, 34] are particularly compelling as they have the potential to save numerous lives [39].”
D Traffic Scene Understanding from Movable Platforms (2013, background): “For a long time, dynamic objects have been considered either in isolation [5], [26], [27], [52] or using simple motion [9], [23], [42], [47], [63] or social interaction [15], [62] models.”
Object Detection With Deep Learning: A Review (2018, background): “[190], person re-identification [191], [192] and robot navigation [193], [194].”