Camera Perception System Patent Landscape 2026
Camera Perception System Patent Landscape in 2026
Scania CV AB commands this field with 41 patent families — nearly three times the next-ranked filer — giving the landscape a strongly concentrated, incumbent-heavy character. Annual volume peaked in 2020 and has eased since, signalling a field past its fastest growth phase, though new entrants in drone and autonomous-vehicle niches continue to arrive.
Scania dominates a concentrated but still-contested field
Scania CV AB holds the top position with 41 patent families, more than three times the 12 held by second-ranked Zoox Inc. The top five filers together account for 51% of the combined output of the hundred largest filers, confirming a highly concentrated competitive structure.
Below Scania there is a clear tier gap: Zoox (12 families), Wing Aviation LLC (11), and Amazon Technologies Inc (8) form a second tier, while the remaining ranked players each hold six or fewer patent families. This two-tier structure means any challenger seeking parity with the leader faces a substantial catch-up distance.
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 1 | Scania CV AB | 41 | |
| 2 | Zoox Inc | 12 | |
| 3 | Wing Aviation LLC | 11 | |
| 4 | Amazon Technologies Inc | 8 | |
| 5 | Juxing Tech (Shenzhen) Co., Ltd. | 6 | |
| 6 | Pebble Mobility Inc | 6 | |
| 7 | Locomation Inc | 5 | |
| 8 | Toyota Motor Corporation | 4 | |
| 9 | Huawei Technologies Co., Ltd. | 4 | |
| 10 | Siemens Corporation | 3 |
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 11 | Qualcomm Incorporated | 3 | |
| 12 | Sikorsky Aircraft Corporation | 3 | |
| 13 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | 3 | |
| 14 | Beijing Xiaomi Mobile Software Co., Ltd. | 3 | |
| 15 | Imago Systems Inc | 2 | |
| 16 | Arriver Software LLC | 2 | |
| 17 | Guangzhou Xpeng Motors Technology Co., Ltd. | 2 | |
| 18 | BAE Systems plc | 2 | |
| 19 | X Development LLC | 2 | |
| 20 | Stack AV Co | 2 |
Scania’s focus on vehicle control and traffic systems (G05D, G08G, B60W) suggests its leadership is rooted in commercial-vehicle autonomy rather than general perception hardware, which may leave adjacent imaging and sensor-fusion branches relatively open to specialists.
Filing counts for 2024–2026 are subject to publication lag and will rise as pending applications publish; the apparent low volume in those years does not necessarily reflect reduced inventor activity. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Filing peaked in 2020; image-recognition and vehicle-control classes dominate the technology mix
The annual filing trend and the IPC technology composition together reveal both the pace of competitive activity and the technical sub-fields attracting the most attention.
Annual filing trend
Filings reached their highest point in 2020 with 26 patent families filed that year, then eased to the mid-teens range through 2022–2023. The 2024–2026 bars are suppressed by publication lag and should not be read as a continuation of the downward trend; the field is past its peak-growth phase on a multi-year basis but not necessarily in terminal contraction.
↗ Hover for values · click a bar to ask EurekaTechnology composition
G06V (image and video recognition) is the dominant IPC class, reflecting core camera-based perception work. G05D (control of non-electric variables) and B60W (hybrid/joint vehicle control) rank second and third, confirming that most filing activity couples perception directly to vehicle or system actuation. G08G (traffic control) and G06T (image data processing) round out the top five, indicating strong interest in both infrastructure-level and algorithmic perception tasks. Lower-volume classes such as B64U (drones), B25J (robotics), and G01S (radar/positioning) signal emerging multi-modal and aerial applications.
↗ Hover for values · click a bar to ask EurekaHighly cited patent families surfaced by the query
Citation-heavy patent families returned by the query. Use this section as citation context, not as a curated list of the most topic-specific patents.
Efficient vision perception
Systems and techniques are provided for vision perception processing. An example method can include determining an attention demand score or characteristic per region of a frame from a sequence of frames; generating attention votes per region of the frame based on the attention demand score or characteristic per region, the attention votes per region… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | Object detection and tracking | 97 |
| 2 | Semantics based safe landing area detection for an… | 84 |
| 3 | Object velocity and/or yaw rate detection and trac… | 46 |
| 4 | Method and control unit for adjusting an inter veh… | 45 |
| 5 | Semantics based safe landing area detection for an… | 30 |
| 6 | Localization by vision | 23 |
| 7 | Semantics based safe landing area detection for an… | 22 |
| 8 | 无人机地面控制系统 | 21 |
Ranked by total forward citations. Citation counts favour older and broadly cited patent families, and broad or adjacent patents may appear when they match the search scope. Treat this section as citation context, not as a curated list of the most topic-specific patents. Some patent titles may be shown in their original, non-English language where an accurate translation could not be guaranteed.
What the patent structure means for R&D investment decisions
The combination of a past-peak filing curve, high concentration, and absent co-filing data points to a field where incumbent depth and solo-filing norms define competitive dynamics.
Past peak: consolidation phase under way
The lifecycle evidence places this field in decline, with annual volume easing back from its 2020 peak. New entrants (Wing Aviation, Pebble Mobility, Huawei, Qualcomm) are still arriving, suggesting selective growth niches remain, but broad-front filing races characteristic of early-growth stages have subsided. R&D investment should target defensible niches rather than broad platform claims.
Lifecycle: DeclineOne dominant incumbent; a shallow second tier
The top five filers account for 51% of the hundred largest filers’ combined output, with Scania alone holding nearly 30% of that group’s total. The tier gap between Scania (41 patent families) and Zoox (12) is large enough that challengers cannot close it quickly through organic filing alone. Acquisition of smaller, focused portfolios — such as those held by Arriver Software or Imago Systems — may be a more efficient path to competitive parity.
High concentrationNo co-applicant activity detected in this corpus
The collaboration evidence shows no recorded co-filing relationships among applicants in this dataset. This suggests the field is characterized by solo, proprietary development rather than consortium or joint-development structures. Entrants should not expect open ecosystem norms; freedom-to-operate analysis and cross-licensing will be more relevant than partnership-based IP sharing.
Solo-filing normsUS-centric filing with selective European and PCT coverage
The United States leads with 54 patent records, followed by the EPO with 30 and WIPO/PCT with 22. Sweden (SE) appears separately with 21 records, reflecting Scania’s home-jurisdiction filings. China shows 11 records, and Germany 7. This distribution suggests that US protection is the primary commercial priority, with selective European and international extension — leaving several major automotive markets with thinner coverage.
US-dominantGo beyond the landscape: Eureka’s TRIZ Solution agent breaks down an R&D problem and returns patented concept solutions, each with a technical approach and cited patent & literature evidence.
Co-filing pairs, ranked by the number of jointly-filed patent families.
Scania leads on vehicle control; drone and AV challengers carving distinct niches
The top two ranked filers pursue different technical strategies: Scania concentrates on commercial-vehicle autonomy and traffic systems, while Zoox focuses on image recognition and image-data processing for robotaxi applications.
Scania CV AB
Scania leads with 41 patent families, concentrated in G05D (control of non-electric variables), G08G (traffic control systems), and B60W (hybrid/joint vehicle control) — a profile oriented toward integrating camera perception into commercial-vehicle autonomy stacks. No momentum data is available for Scania in the recent-versus-prior comparison, indicating the bulk of its portfolio was established in prior periods rather than being a recent surge.
families: 41Zoox Inc
Zoox holds 12 patent families, with emphasis on G06V (image/video recognition) and G06T (image data processing), plus B60W (vehicle control) — reflecting a robotaxi perception stack focused on visual understanding. Wing Aviation LLC (11 families, new entrant with 8 recent patent families) is an equally prominent challenger, concentrating on G06V and B64U (drone applications), making it the leading aerial-perception filer in this corpus.
families: 12| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| Wing Aviation LLC | 8 | ▲ new entrant |
| Amazon Technologies Inc | 2 | ▲ new entrant |
| Pebble Mobility Inc | 5 | ▲ new entrant |
| Huawei Technologies Co., Ltd. | 2 | ▲ new entrant |
| Qualcomm Incorporated | 2 | ▲ new entrant |
Under-served branches in sensor fusion, positioning, and data processing
Several IPC classes adjacent to the dominant image-recognition core show relatively low filing shares, warranting attention from teams evaluating where perception IP coverage is thin.
G01S · Radar, sonar & positioning
With 23 patent records and a 5% share among the top-ranked filers, radar and active-sensor positioning is an adjacent branch with limited dedicated coverage relative to camera-only approaches. Camera-plus-LiDAR or camera-plus-radar fusion is a well-established engineering path for robust perception in adverse conditions, yet the corpus shows few families specifically bridging G06V and G01S. Teams with sensor-fusion expertise could file in this gap; the entry path is technically demanding but the incumbent depth here is shallow compared with the main G06V cluster.
Search this in Eureka →G01C · Distance, navigation & gyroscopes
G01C (distance, navigation, and gyroscopes) holds only 16 patent records and a 4% share, despite camera-based localization being a core capability for autonomous vehicles and drones. The most-cited work in this corpus includes a ‘Localization by vision’ patent (23 citations), indicating technical relevance — yet filing volume is sparse. Applicants focusing on visual odometry, camera-inertial odometry, or HD-map-free localization could find meaningful white space here, particularly for non-automotive platforms such as aerial or agricultural robots.
Search this in Eureka →How leaders differ across technology routes
Strength of each leader across the main technology routes.
| Player | G06V 20 · Image/video recognition | G05D 1 · Control of non-electric variables | G06V 10 · Image/video recognition | G06T 7 · Image data processing & generation | G08G 1 · Traffic control systems |
|---|---|---|---|---|---|
| Scania CV AB | Moderate · 10 | Strong · 29 | Emerging · 5 | Moderate · 7 | Strong · 25 |
| Zoox Inc | Moderate · 4 | Moderate · 4 | Strong · 12 | Strong · 9 | Absent |
| Wing Aviation LLC | Strong · 11 | Emerging · 2 | Moderate · 5 | Moderate · 3 | Absent |
| Huawei Technologies Co., Ltd. | Strong · 4 | Absent | Moderate · 2 | Moderate · 2 | Absent |
| Toyota Research Institute Inc. | Moderate · 2 | Strong · 4 | Absent | Moderate · 2 | Absent |
| Locomation Inc | Absent | Strong · 4 | Absent | Absent | Strong · 4 |
| Amazon Technologies Inc | Strong · 7 | Absent | Absent | Absent | Absent |
Frequently asked questions
Scania CV AB leads with 41 patent families, which is nearly three times the portfolio of second-ranked Zoox Inc (12 patent families). Scania’s filings are concentrated in vehicle control and traffic management IPC classes.
Annual filings peaked in 2020 with 26 patent families filed that year, then eased through 2021–2023. The field is past its fastest-growth phase. Figures for 2024–2026 are suppressed by publication lag and should not be interpreted as a sustained decline.
G06V (image and video recognition) is the most active IPC class, followed by G05D (control of non-electric variables), B60W (hybrid/joint vehicle control), G08G (traffic control), and G06T (image data processing). Together these classes reflect a field that tightly couples camera perception to downstream vehicle or system actuation.
The United States is the leading filing jurisdiction with 54 patent records, followed by the EPO with 30, WIPO/PCT with 22, Sweden with 21, and China with 11. This distribution reflects both the US-heavy applicant base and Scania’s home-jurisdiction filings in Sweden.
No co-applicant filing relationships are recorded in the current evidence for this corpus. The landscape appears to be characterized by solo, proprietary development across all ranked applicants.
G01S (radar, sonar, and positioning) and G01C (distance, navigation, and gyroscopes) are the two branches with plausible technical adjacency to camera perception but relatively low filing shares — 5% and 4% respectively among the corpus. G06T (image data processing) and G06K (data recognition) also show limited coverage relative to the dominant G06V class.
Ready to map your own camera perception landscape?
Join 18,000+ innovators using PatSnap Eureka to map any technology landscape: search 2B+ patents and papers, surface key assignees, and generate a report like this in minutes.
Disclaimer. This page is generated from PatSnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. PatSnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.